INDEX

Explanations

structured information about companies and their activities

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

 Greens

-0.14

eral

-0.14

Æ°Æ¡ng

-0.14

ampa

-0.14

ãģĿãģĹãģ¦

-0.14

erial

-0.13

erson

-0.13

POSITIVE LOGITS

Responder

0.17

 PERMISSION

0.16

ullet

0.15

esub

0.15

kul

0.14

å¤

0.14

 meis

0.14

 ÑĤÐµÑħ

0.14

Kul

0.14

kc

0.14

Activations Density 0.251%

structured information about companies and their activities

No Comments

No Known Activations