INDEX

Explanations

assertions regarding dependent relationships and influences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

ritz

-0.16

ead

-0.16

 alone

-0.16

 fraught

-0.15

 Cherry

-0.15

licit

-0.15

-0.14

 compens

-0.14

 cher

-0.14

wen

-0.14

POSITIVE LOGITS

 influenced

0.35

 dependent

0.31

 driven

0.27

dependent

0.27

affected

0.27

 shaped

0.27

 affected

0.27

 depend

0.25

 determined

0.24

 contingent

0.23

Activations Density 0.190%

assertions regarding dependent relationships and influences

No Comments

No Known Activations