INDEX

Explanations

words related to change and transitions in contexts like employment and media representation

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

ãģŁãģ¡ãģ®

-0.15

 milfs

-0.14

èµĸ

-0.14

ilip

-0.14

 gezocht

-0.13

 dÃ¢n

-0.13

&r

-0.13

heed

-0.13

ĶĶ

-0.13

POSITIVE LOGITS

 hack

0.17

its

0.16

Ã¢n

0.15

 Dict

0.15

 involved

0.15

 providing

0.15

 intervene

0.15

neau

0.15

 coming

0.15

 cruc

0.14

Activations Density 0.431%

words related to change and transitions in contexts like employment and media representation

No Comments

No Known Activations