INDEX

Explanations

code-related keywords and annotations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

/loose

-0.16

itness

-0.15

ãĥ³ãĥĨ

-0.14

ascus

-0.14

lash

-0.14

Å¡Å¡ÃŃ

-0.14

esteem

-0.13

ç²¾åĵģ

-0.13

gua

-0.13

atalog

-0.13

POSITIVE LOGITS

 rocker

0.14

 Sext

0.14

Ïħ

0.14

ffffffff

0.14

ponder

0.13

zip

0.13

FA

0.13

 Duffy

0.13

atomic

0.13

ionale

0.13

Activations Density 0.012%

code-related keywords and annotations

No Comments

No Known Activations