INDEX

Explanations

specific locations and addresses

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

aux

-0.16

zia

-0.15

eci

-0.15

ertino

-0.15

 createState

-0.14

aj

-0.14

upa

-0.14

 sant

-0.13

vod

-0.13

 Sears

-0.13

POSITIVE LOGITS

 street

0.75

 Street

0.71

street

0.65

Street

0.63

 STREET

0.62

_street

0.52

.street

0.51

 streets

0.51

è¡Ĺ

0.45

 Streets

0.45

Activations Density 0.113%

specific locations and addresses

No Comments

No Known Activations