INDEX

Explanations

references to press releases

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

uteur

-0.21

hs

-0.16

ts

-0.15

tes

-0.15

wner

-0.15

-0.14

.InnerText

-0.14

tsy

-0.14

zego

-0.14

WISE

-0.14

POSITIVE LOGITS

uring

0.16

sed

0.15

ÐµÐ³Ð°

0.15

light

0.14

ings

0.14

nya

0.14

ibly

0.14

nick

0.14

ibur

0.14

uf

0.13

Activations Density 0.019%

references to press releases

No Comments

No Known Activations

references to press releases

No Comments

No Known Activations