INDEX

Explanations

references to workplace safety issues

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

Veg

-0.16

antaged

-0.16

å¬

-0.14

ideographic

-0.14

atte

-0.13

 INCIDENT

-0.13

 Fountain

-0.13

 insol

-0.12

 detriment

-0.12

 equivalents

-0.12

POSITIVE LOGITS

Ã©ri

0.15

eer

0.15

_tac

0.15

sono

0.15

anine

0.14

uri

0.14

 ticking

0.14

prene

0.14

 inher

0.14

ook

0.14

Activations Density 0.275%

references to workplace safety issues

No Comments

No Known Activations