INDEX

Explanations

words indicating responsibility or obligation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

 Pest

-0.17

(IService

-0.15

oui

-0.15

 Quar

-0.14

 irres

-0.14

ombine

-0.14

ayi

-0.13

 weitere

-0.13

EATURE

-0.13

ì¸ł

-0.13

POSITIVE LOGITS

-share

0.16

 voluntary

0.16

 sharing

0.16

 volcano

0.15

 SHARE

0.15

 piece

0.15

.vol

0.15

Vol

0.15

Vol

0.15

bi

0.15

Activations Density 0.028%

words indicating responsibility or obligation

No Comments

No Known Activations