INDEX

Explanations

mentions of legal or governmental actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

 conservatives

-0.18

 conservative

-0.18

 conserv

-0.17

olini

-0.17

 conservatism

-0.16

endor

-0.15

 conserve

-0.15

å®Ī

-0.15

FORMANCE

-0.15

.Transactional

-0.15

POSITIVE LOGITS

 progressive

0.18

 Progressive

0.18

 Higgins

0.15

 Henderson

0.15

ayas

0.15

arie

0.15

ayah

0.15

ayar

0.14

soft

0.14

aptop

0.14

Activations Density 0.466%

mentions of legal or governmental actions

No Comments

No Known Activations