INDEX

Explanations

phrases expressing intentions or goals

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

sb

-0.16

omm

-0.15

onym

-0.15

åĲ

-0.15

ltk

-0.15

elf

-0.14

hest

-0.14

erville

-0.14

 Ames

-0.14

ÑģÑĤÑĢÐ°

-0.13

POSITIVE LOGITS

usi

0.16

locker

0.16

Ĳ

0.16

ansa

0.15

olds

0.15

 Mand

0.14

imitives

0.14

ProgressHUD

0.14

 Graham

0.14

alin

0.14

Activations Density 0.025%

phrases expressing intentions or goals

No Comments

No Known Activations