INDEX

Explanations

phrases indicating structured processes or step-by-step instructions

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

enga

-0.15

rung

-0.15

ihan

-0.14

bid

-0.14

%X

-0.14

éĽħ

-0.14

sted

-0.14

stock

-0.14

edImage

-0.14

ulist

-0.13

POSITIVE LOGITS

opc

0.17

opus

0.15

-Compatible

0.14

kip

0.14

appen

0.14

 Labs

0.14

 Snape

0.14

ocu

0.13

alion

0.13

OUNT

0.13

Activations Density 0.006%

phrases indicating structured processes or step-by-step instructions

No Comments

No Known Activations