INDEX

Explanations

instances of past and present tense verbs, particularly focusing on actions and conditions

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

bon

-0.16

ĥ

-0.14

Ø²Ø©

-0.14

istani

-0.14

ahr

-0.14

notice

-0.14

eller

-0.13

endant

-0.13

 ìĻ¸

-0.13

Shell

-0.13

POSITIVE LOGITS

 itself

0.17

gies

0.17

egra

0.16

lets

0.16

YLES

0.15

hone

0.15

ivals

0.15

letics

0.14

mac

0.14

ÑħÐ¸

0.14

Activations Density 0.416%

instances of past and present tense verbs, particularly focusing on actions and conditions

No Comments

No Known Activations