INDEX

Explanations

discussions surrounding threats and their implications on safety

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

ovsky

-0.16

Ã©gor

-0.15

argas

-0.15

-0.14

 Victims

-0.14

alez

-0.14

artin

-0.14

otos

-0.14

 tmpl

-0.14

POSITIVE LOGITS

 threat

0.59

 threats

0.52

threat

0.50

 Threat

0.49

å¨ģ

0.49

-threat

0.49

Th

0.48

 danger

0.42

 threatening

0.40

TH

0.40

Activations Density 0.157%

discussions surrounding threats and their implications on safety

No Comments

No Known Activations