INDEX

Explanations

references to women and their experiences or allegations

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

kop

-0.18

à¸§à¸ģ

-0.15

åĭ

-0.15

ÎĲ

-0.14

HEMA

-0.14

kre

-0.14

 ÑģÐ¿ÑĢÑı

-0.14

ondo

-0.13

loh

-0.13

referer

-0.13

POSITIVE LOGITS

 forward

0.84

 Forward

0.71

forward

0.71

Forward

0.65

-forward

0.63

 FORWARD

0.58

 forwards

0.55

_forward

0.54

 forth

0.53

fwd

0.52

Activations Density 0.070%

references to women and their experiences or allegations

No Comments

No Known Activations