INDEX

Explanations

punctuation and formatting in written text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

reeze

-0.15

ference

-0.14

ÏīÎ¼Î±

-0.14

 ìĿ¼ë°ĺ

-0.14

LinkId

-0.14

heck

-0.13

.nextSibling

-0.13

obo

-0.13

hea

-0.13

éĴ®

-0.13

POSITIVE LOGITS

 onto

0.19

 Where

0.17

 into

0.17

aclass

0.16

don

0.16

 Â¡

0.16

 time

0.15

mrb

0.15

let

0.15

 What

0.15

Activations Density 0.214%

punctuation and formatting in written text

No Comments

No Known Activations