INDEX

Explanations

adverbs indicating the quality or condition of objects and actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

arat

-0.17

ettings

-0.15

deen

-0.15

stru

-0.15

.scalablytyped

-0.15

.gdx

-0.15

EMPLARY

-0.14

à¤¦à¤°

-0.14

empor

-0.14

 getNext

-0.14

POSITIVE LOGITS

vrier

0.17

esch

0.15

incinn

0.14

ÑĢÑĸÑĩ

0.14

zda

0.14

ÛĮØ±ÛĮ

0.13

çļĦäºĭ

0.13

ç»ĥ

0.13

nat

0.13

ĸī

0.13

Activations Density 0.204%

adverbs indicating the quality or condition of objects and actions

No Comments

No Known Activations