INDEX

Explanations

references to safety and health-related topics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

Î´Î¿

-0.17

Toolkit

-0.17

holm

-0.17

hol

-0.15

 Toolkit

-0.14

Ð¸ÑĩÐ°

-0.14

.getAs

-0.14

/Set

-0.14

ä¹İ

-0.14

lt

-0.14

POSITIVE LOGITS

ghan

0.17

cran

0.14

owler

0.14

hangi

0.14

éļ

0.14

case

0.14

lian

0.14

Ø§ØªÙĩ

0.14

thed

0.14

 kari

0.14

Activations Density 0.423%

references to safety and health-related topics

No Comments

No Known Activations