INDEX

Explanations

sections that provide organized information about items and their related details

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

pons

-0.17

NSE

-0.15

ì²Ń

-0.15

iceps

-0.14

ropa

-0.14

agens

-0.14

Avg

-0.14

 ÐºÐ¾Ð½ÑĤÑĢÐ°

-0.13

awn

-0.13

oser

-0.13

POSITIVE LOGITS

 Lords

0.15

Ney

0.14

rray

0.14

ãĥ³ãĥĩ

0.14

ERGE

0.14

ignum

0.13

Â´:

0.13

OMATIC

0.13

åĩ

0.13

à¹Ħ

0.13

Activations Density 0.033%

sections that provide organized information about items and their related details

No Comments

No Known Activations