INDEX

Explanations

instances of comments or annotations in the code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

oste

-0.16

ovich

-0.15

ches

-0.15

_none

-0.15

steen

-0.15

 âĨĴ↵↵

-0.14

_picker

-0.14

é¸Ł

-0.14

ç´¹

-0.14

ħį

-0.14

POSITIVE LOGITS

ominator

0.16

 Friendship

0.14

inger

0.14

 Clifford

0.14

onym

0.14

bao

0.14

erville

0.14

omial

0.14

 Assistant

0.14

 Chow

0.13

Activations Density 0.016%

instances of comments or annotations in the code

No Comments

No Known Activations