INDEX

Explanations

instances of the word "adopt" and its variations

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

Ð»ÑĮ

-0.15

onders

-0.15

am

-0.14

rhs

-0.14

.createObject

-0.14

erk

-0.14

ufac

-0.14

 å®®

-0.13

nder

-0.13

/no

-0.13

POSITIVE LOGITS

able

0.17

 Adopt

0.15

resher

0.15

cplusplus

0.15

wap

0.15

adopt

0.14

otron

0.14

amas

0.14

 Crowley

0.14

genes

0.14

Activations Density 0.020%

instances of the word "adopt" and its variations

No Comments

No Known Activations