INDEX

Explanations

statistical percentages and survey data

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

loi

-0.15

heads

-0.14

ONGL

-0.14

-0.13

coni

-0.13

UBLE

-0.13

tero

-0.13

/trunk

-0.13

empo

-0.12

 nied

-0.12

POSITIVE LOGITS

 other

0.16

 ê¸°íĥĢ

0.15

 mixed

0.15

DOI

0.15

 Mixed

0.15

Meh

0.15

 blank

0.15

 unsure

0.15

 Huck

0.15

UNKNOWN

0.15

Activations Density 0.065%

statistical percentages and survey data

No Comments

No Known Activations