INDEX

Explanations

references to political groups and their interactions with societal conflicts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

Ø·Ø§ÙĤ

-0.15

ynet

-0.14

æ±Ĺ

-0.14

oldur

-0.13

PAIR

-0.13

 kÃ¥

-0.13

utz

-0.13

blr

-0.12

sov

-0.12

UILT

-0.12

POSITIVE LOGITS

 sympathetic

0.36

 opposed

0.35

 allied

0.34

 aligned

0.33

 supportive

0.32

 hostile

0.32

 loyal

0.29

 friendly

0.28

 opposing

0.28

 bent

0.28

Activations Density 0.332%

references to political groups and their interactions with societal conflicts

No Comments

No Known Activations