INDEX

Explanations

block comments in code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

toi

-0.15

 Sick

-0.14

enberg

-0.14

æ¯Ĵ

-0.14

Ð¸ÐºÐ¸

-0.14

per

-0.14

inand

-0.14

ëıĦë¡Ŀ

-0.13

 Exchange

-0.13

perate

-0.13

POSITIVE LOGITS

0.17

0.16

Ã¨s

0.16

0.15

ies

0.15

Ã¡o

0.15

zer

0.14

Activations Density 0.021%

block comments in code

No Comments

No Known Activations