INDEX

Explanations

references to academic and industry settings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

ahn

-0.21

WithTag

-0.14

odos

-0.13

iro

-0.13

Drawable

-0.13

|--------------------------------------------------------------------------↵

-0.13

kos

-0.13

andi

-0.13

ERN

-0.12

ernity

-0.12

POSITIVE LOGITS

 into

0.58

 onto

0.54

into

0.50

 Into

0.49

Into

0.48

onto

0.45

_into

0.44

 INTO

0.43

 toward

0.34

 towards

0.33

Activations Density 0.235%

references to academic and industry settings

No Comments

No Known Activations