INDEX

Explanations

comments and preprocessor directives 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 @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

ful

-0.15

-0.14

 ekip

-0.14

avax

-0.14

idal

-0.14

usta

-0.14

 Atlas

-0.13

__(*

-0.13

idae

-0.13

POSITIVE LOGITS

ubat

0.16

Ã²i

0.16

ChildIndex

0.15

kop

0.15

bsolute

0.14

ÙĤØª

0.14

keh

0.14

ÙĬÙĨØ§

0.14

erland

0.14

wear

0.14

Activations Density 0.003%

comments and preprocessor directives in code

No Comments

No Known Activations