INDEX

Explanations

comparative phrases and statements that denote significance or importance

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

//[

-0.16

 Kahn

-0.15

thesis

-0.15

Ð¾ÑıÐ½

-0.15

enko

-0.15

elly

-0.15

toMatch

-0.14

YK

-0.14

acas

-0.14

rio

-0.14

POSITIVE LOGITS

 than

0.55

than

0.43

-than

0.43

 Than

0.40

 THAN

0.40

Than

0.40

_than

0.37

 niÅ¼

0.28

_THAN

0.26

 neÅ¾

0.26

Activations Density 0.306%

comparative phrases and statements that denote significance or importance

No Comments

No Known Activations