INDEX

Explanations

subjective claims or opinions about people's behavior or situations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

 scratch

-0.16

awah

-0.15

acomment

-0.15

yer

-0.15

ying

-0.15

 Kurum

-0.15

ssa

-0.14

ÐµÐ²Ð¸Ñĩ

-0.14

ynos

-0.14

hud

-0.14

POSITIVE LOGITS

ÙĨÛĮ

0.15

 interven

0.15

tron

0.15

 repl

0.14

zac

0.14

Crud

0.14

URLRequest

0.14

izo

0.14

zav

0.13

uke

0.13

Activations Density 0.112%

subjective claims or opinions about people's behavior or situations

No Comments

No Known Activations