INDEX

Explanations

instances of commas and the word "a" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

zman

-0.15

åĿĤ

-0.14

erf

-0.14

unda

-0.14

/embed

-0.13

bol

-0.13

à¸ļà¸²à¸ĩ

-0.13

eme

-0.13

ahat

-0.13

ugu

-0.13

POSITIVE LOGITS

 Barbar

0.16

CJK

0.14

ulfilled

0.14

ÄĽtÃŃ

0.14

apur

0.14

-widgets

0.14

asi

0.14

phalt

0.13

adays

0.13

ansi

0.13

Activations Density 0.029%

instances of commas and the word "a" in various contexts

No Comments

No Known Activations