INDEX

Explanations

numerical information associated with data or statistics

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

imos

-0.15

endimento

-0.14

itur

-0.14

ahat

-0.14

 coma

-0.14

auses

-0.14

à¥ģà¤°à¤¸

-0.13

ifie

-0.13

 ÐºÐ¾Ð¼

-0.13

omer

-0.13

POSITIVE LOGITS

alto

0.17

0.16

 Dawson

0.15

ANNEL

0.15

?action

0.15

elly

0.14

Ø±Ùģ

0.14

-du

0.14

Activations Density 0.269%

numerical information associated with data or statistics

No Comments

No Known Activations