INDEX

Explanations

instances of bullying and related experiences or themes

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

ocaly

-0.16

POSE

-0.15

adio

-0.15

 prostit

-0.14

 prostitute

-0.14

bab

-0.14

 treason

-0.14

oice

-0.14

Accessory

-0.14

UTO

-0.13

POSITIVE LOGITS

 bullying

0.40

 bully

0.35

bul

0.32

Bul

0.32

 bullied

0.32

 peer

0.28

 bull

0.26

 Peer

0.26

 peers

0.25

Peer

0.24

Activations Density 0.043%

instances of bullying and related experiences or themes

No Comments

No Known Activations