INDEX

Explanations

proper nouns, especially names of players and teams

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

.tk

-0.16

 getch

-0.16

Î»Ïī

-0.15

á»©a

-0.15

.hu

-0.14

Blank

-0.14

arro

-0.14

arov

-0.14

à¸Ńà¸ĩ

-0.14

bben

-0.14

POSITIVE LOGITS

çħ

0.15

undles

0.15

 prima

0.14

ates

0.14

ugin

0.14

ombres

0.13

 Bureau

0.13

.pb

0.13

usic

0.13

Activations Density 0.055%

proper nouns, especially names of players and teams

No Comments

No Known Activations