INDEX

Explanations

references to organized information and relationships in a structured context

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

illard

-0.16

/OR

-0.16

aupt

-0.15

 çĶŁåĳ½åĳ¨æľŁåĩ½æķ°

-0.14

yonel

-0.14

ysa

-0.14

ropri

-0.14

exampleModal

-0.13

ìķ¡

-0.13

POSITIVE LOGITS

 having

0.36

 together

0.34

 along

0.32

 using

0.32

having

0.32

using

0.31

along

0.31

 Together

0.29

 Having

0.29

 Along

0.28

Activations Density 0.043%

references to organized information and relationships in a structured context

No Comments

No Known Activations