INDEX

Explanations

instances of the letter "h" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

Hub

-0.15

mitter

-0.14

idUser

-0.14

eyn

-0.14

oti

-0.14

à¥įà¤°à¤¤

-0.14

esk

-0.14

Ã¶

-0.14

Hub

-0.13

orida

-0.13

POSITIVE LOGITS

istrovstvÃŃ

0.19

æµ¦

0.17

urr

0.17

iola

0.16

ate

0.16

PLUS

0.16

 tail

0.15

.url

0.15

URT

0.15

ates

0.15

Activations Density 0.025%

instances of the letter "h" in various contexts

No Comments

No Known Activations