INDEX

Explanations

references to smoking and related behaviors

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

-0.15

_plural

-0.15

ichel

-0.15

-0.14

edition

-0.14

_exempt

-0.14

ulkan

-0.14

Unnamed

-0.13

POSITIVE LOGITS

etas

0.18

haven

0.16

erp

0.15

bilt

0.15

bens

0.14

/tos

0.14

 tobacco

0.14

ableObject

0.14

ARA

0.14

ark

0.14

Activations Density 0.011%

references to smoking and related behaviors

No Known Activations