INDEX

Explanations

phrases related to liability and insurance coverage

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

nett

-0.17

cord

-0.15

uur

-0.15

bane

-0.15

 Balt

-0.14

ARING

-0.14

Ð½ÐµÑĢ

-0.14

ãģĭãģĹ

-0.14

 backlog

-0.14

nero

-0.14

POSITIVE LOGITS

 coverage

0.44

 Coverage

0.40

coverage

0.40

Coverage

0.38

 insurance

0.33

 protection

0.32

_coverage

0.30

 cover

0.30

 Cover

0.27

 Protection

0.27

Activations Density 0.091%

phrases related to liability and insurance coverage

No Comments

No Known Activations