INDEX

Explanations

expressions of personal opinions and emotional responses to experiences or preferences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

ÐµÐ»ÐµÑĦ

-0.16

åĿĬ

-0.14

Ð»ÑĥÑĩ

-0.14

NAL

-0.14

idon

-0.13

->{_

-0.13

FML

-0.13

immel

-0.13

Ð²ÑģÑı

-0.13

ãĤ¯ãĥĪ

-0.13

POSITIVE LOGITS

 enjoy

0.54

 likes

0.51

 enjoys

0.50

 enjoying

0.49

 love

0.48

 liked

0.47

 enjoyed

0.47

 Enjoy

0.47

 liking

0.46

 loves

0.42

Activations Density 0.491%

expressions of personal opinions and emotional responses to experiences or preferences

No Comments

No Known Activations