INDEX

Explanations

references to legal and administrative terminology

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

åºŃ

-0.17

braco

-0.17

_four

-0.16

Ì§

-0.15

iente

-0.15

fos

-0.15

âĢİ

-0.15

izard

-0.15

ulaire

-0.14

ertino

-0.13

POSITIVE LOGITS

0.24

//{{

0.15

{{{

0.14

.Transactional

0.14

NaN

0.14

ÎĹÎľ

0.13

 Infinity

0.13

ritch

0.13

 noon

0.13

ë°Ģ

0.13

Activations Density 0.357%

references to legal and administrative terminology

No Comments

No Known Activations