INDEX

Explanations

addresses and location names

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

 downtown

-0.17

 Downtown

-0.15

oze

-0.15

achu

-0.15

ousel

-0.15

WebRequest

-0.14

Ä©nh

-0.14

Î¼Î²

-0.14

ÑĨÐ²ÐµÑĤ

-0.14

orea

-0.14

POSITIVE LOGITS

ely

0.17

 Broadcast

0.16

 Telecom

0.15

 Mastery

0.14

.dev

0.14

 Dipl

0.14

 Ambassador

0.14

agh

0.14

erus

0.14

fi

0.14

Activations Density 0.099%

addresses and location names

No Comments

No Known Activations