INDEX

Explanations

phrases that indicate a relationship or association

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

ocket

-0.15

 Seah

-0.14

ayo

-0.14

ope

-0.14

nul

-0.14

-Ð»Ð¸

-0.13

 Pride

-0.13

jÃŃ

-0.13

uffer

-0.13

velt

-0.13

POSITIVE LOGITS

.scalablytyped

0.17

ien

0.16

WO

0.15

osis

0.15

antes

0.15

obia

0.15

antis

0.15

indsay

0.14

Activations Density 0.043%

phrases that indicate a relationship or association

No Comments

No Known Activations