INDEX

Explanations

references to the Associated Press

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

ÐŁÐļ

-0.17

ê¶Į

-0.16

azzo

-0.15

pir

-0.15

alf

-0.15

atorium

-0.14

à¥°

-0.14

anh

-0.14

acter

-0.14

elli

-0.13

POSITIVE LOGITS

 Press

0.22

Press

0.20

 press

0.17

RICS

0.16

ottes

0.15

 Mond

0.14

 Bradford

0.14

_press

0.14

press

0.14

dia

0.14

Activations Density 0.006%

references to the Associated Press

No Comments

No Known Activations