INDEX

Explanations

conversational phrases discussing potential risks and challenges

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

este

-0.14

Ð¨ÐĲ

-0.14

mez

-0.14

 UObject

-0.13

Ã©lÃ©

-0.13

xygen

-0.13

ilha

-0.13

omez

-0.13

phys

-0.13

pper

-0.13

POSITIVE LOGITS

 pose

0.75

 poses

0.69

 presents

0.69

 Pose

0.60

 posing

0.59

 posed

0.58

Pose

0.58

pose

0.57

 presenting

0.55

 Presents

0.55

Activations Density 0.346%

conversational phrases discussing potential risks and challenges

No Comments

No Known Activations