INDEX

Explanations

references to vulnerable individuals or groups in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

tron

-0.16

nd

-0.16

 Stateless

-0.15

ntl

-0.15

ually

-0.14

uel

-0.14

yen

-0.14

wang

-0.13

à¸²à¸£à¸ĸ

-0.13

aries

-0.13

POSITIVE LOGITS

who

0.16

 Ð¶Ðµ

0.16

-ci

0.15

zelf

0.14

Ļ¨

0.14

 same

0.14

 Marcus

0.14

Ð¾ÑĢÐ¸

0.13

errat

0.13

dsn

0.13

Activations Density 0.053%

references to vulnerable individuals or groups in various contexts

No Comments

No Known Activations