INDEX

Explanations

references to various types of threats

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

iao

-0.20

oya

-0.18

inho

-0.16

ocker

-0.16

ilton

-0.15

artin

-0.15

WARD

-0.14

.pixel

-0.14

ocket

-0.14

ity

-0.14

POSITIVE LOGITS

 posed

0.29

ening

0.24

ened

0.23

Pos

0.19

 pose

0.19

posed

0.18

pose

0.18

ener

0.18

 danger

0.18

å¨ģ

0.17

Activations Density 0.028%

references to various types of threats

No Comments

No Known Activations