INDEX

Explanations

phrases that express comparisons and contrast between different entities or concepts

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

iddi

-0.18

eydi

-0.16

arme

-0.15

imore

-0.15

ÙĦØ§ÙĦ

-0.15

 kendine

-0.15

tÃŃ

-0.14

unte

-0.14

ëĵ

-0.14

_gem

-0.14

POSITIVE LOGITS

 compare

0.41

 compares

0.41

 match

0.39

 rival

0.34

 Compare

0.34

match

0.31

 matches

0.31

 comparison

0.31

compare

0.31

 comparing

0.31

Activations Density 0.092%

phrases that express comparisons and contrast between different entities or concepts

No Comments

No Known Activations