INDEX

Explanations

references to attitudes and cultural values

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

erce

-0.17

SupportedContent

-0.17

zk

-0.15

fall

-0.15

lette

-0.15

holm

-0.15

falls

-0.15

lsen

-0.15

ERY

-0.14

Sta

-0.14

POSITIVE LOGITS

 toward

0.20

 towards

0.20

 attitudes

0.19

 attitude

0.18

cnt

0.15

 disposition

0.15

ãĤĵãģ©

0.15

åĲĳ

0.15

Tow

0.15

Activations Density 0.062%

references to attitudes and cultural values

No Comments

No Known Activations