INDEX

Explanations

references to death or dying

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

ial

-0.17

ipro

-0.15

Ø§Ø±Ùĩ

-0.15

ver

-0.15

insky

-0.15

ours

-0.15

mi

-0.14

ifetime

-0.14

ë§Į

-0.14

rette

-0.14

POSITIVE LOGITS

lectric

0.21

 young

0.18

 intest

0.18

elp

0.17

hard

0.16

daÅŁ

0.16

young

0.15

 defending

0.15

 Lambert

0.15

-hard

0.15

Activations Density 0.025%

references to death or dying

No Comments

No Known Activations