INDEX

Explanations

numerical data and statistics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

Ĭ¶

-0.16

ernet

-0.15

iman

-0.14

ongs

-0.14

ç©¶

-0.14

Tol

-0.14

æĽ¼

-0.13

ëł¨

-0.13

thouse

-0.13

ihat

-0.13

POSITIVE LOGITS

ande

0.15

endoza

0.15

desk

0.14

Ð¾Ð·ÐµÐ¼

0.14

ancellable

0.14

SqlParameter

0.14

åıĸæ¶Ī

0.14

 glGetUniformLocation

0.14

0.13

Activations Density 0.173%

numerical data and statistics

No Comments

No Known Activations