INDEX

Explanations

instances of the word "abuse" and related terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

æı

-0.15

Ð¾Ð±Ð¸

-0.14

uture

-0.14

iliz

-0.14

ãĤ·ãĤ¢

-0.13

ØªØ§ÙĨ

-0.13

ari

-0.13

stad

-0.13

anders

-0.13

ling

-0.13

POSITIVE LOGITS

amac

0.18

fully

0.16

 ÙħÙĤØ¯

0.14

ena

0.13

antly

0.13

ASON

0.13

 Ansi

0.13

ongyang

0.13

builtin

0.13

Activations Density 0.011%

instances of the word "abuse" and related terms

No Comments

No Known Activations