INDEX

Explanations

instances of the word "revisit" and its variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

reur

-0.15

Î¸ÎµÎ¯

-0.15

tank

-0.15

eza

-0.14

mo

-0.14

tip

-0.14

íĶ¼

-0.14

 Impress

-0.14

Bet

-0.14

tere

-0.14

POSITIVE LOGITS

ited

0.28

iting

0.26

ual

0.26

iÃ³n

0.19

es

0.18

ory

0.18

ers

0.17

ngle

0.17

als

0.17

ists

0.17

Activations Density 0.003%

instances of the word "revisit" and its variations

No Comments

No Known Activations