INDEX

Explanations

references to answers or responses in discussions or questions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

irst

-0.18

geb

-0.18

ernen

-0.16

side

-0.16

gio

-0.15

gia

-0.15

PEED

-0.15

Ø±Ø§ÙĤ

-0.15

Ã©c

-0.15

audi

-0.15

POSITIVE LOGITS

er

0.22

phone

0.18

able

0.18

ToSelector

0.17

ing

0.16

 questions

0.16

nable

0.16

/address

0.15

ative

0.15

atives

0.15

Activations Density 0.027%

references to answers or responses in discussions or questions

No Comments

No Known Activations