INDEX

Explanations

references to a cast or actors in films or shows

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

ane

-0.16

uai

-0.15

ury

-0.15

ibus

-0.15

 optional

-0.14

ag

-0.14

 ActionTypes

-0.14

als

-0.13

...

-0.13

mes

-0.13

POSITIVE LOGITS

'gc

0.18

posix

0.15

Ð»ÑĸÐ½Ð½Ñı

0.15

 lá»ĩ

0.14

renom

0.14

ÄĻk

0.14

åºŃ

0.14

achen

0.14

ALAR

0.14

okane

0.14

Activations Density 0.017%

references to a cast or actors in films or shows

No Comments

No Known Activations