INDEX

Explanations

references to news and media content

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

emos

-0.16

wer

-0.15

 enforce

-0.14

åĽ³

-0.14

enz

-0.14

 cÃ´t

-0.13

enÃŃ

-0.13

_LICENSE

-0.13

.inspect

-0.13

ìĭ¬

-0.13

POSITIVE LOGITS

 news

0.18

 newsp

0.15

 headlines

0.15

 press

0.15

ouble

0.15

news

0.15

 dated

0.15

 updates

0.15

 recent

0.15

/news

0.14

Activations Density 0.085%

references to news and media content

No Comments

No Known Activations