INDEX

Explanations

lines of code or comments in programming-related text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

gens

-0.16

-0.14

ils

-0.14

utin

-0.14

ares

-0.14

Ð³Ð°Ð»

-0.14

heiro

-0.13

aya

-0.13

Ð¾Ñī

-0.13

xima

-0.13

POSITIVE LOGITS

oldem

0.15

ifu

0.14

 (!((

0.14

blr

0.14

kaar

0.14

á¿Ĩ

0.14

ryn

0.14

Ã¡c

0.14

Î¯Î³

0.13

ury

0.13

Activations Density 0.083%

lines of code or comments in programming-related text

No Comments

No Known Activations

lines of code or comments in programming-related text

No Comments

No Known Activations