INDEX

Explanations

references to articles, readings, or suggested related content

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

ë¥ĺ

-0.16

iov

-0.16

mund

-0.15

ruÅ¾

-0.15

.ds

-0.15

ander

-0.14

orce

-0.14

 sublic

-0.14

ianne

-0.14

 ØµÙģ

-0.14

POSITIVE LOGITS

 grav

0.15

VC

0.15

anou

0.14

how

0.14

çĶ

0.14

ddy

0.14

upo

0.13

How

0.13

Inc

0.13

Activations Density 0.006%

references to articles, readings, or suggested related content

No Comments

No Known Activations