INDEX

Explanations

version numbers or version-related information

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

enÃŃ

-0.15

Ìĥ

-0.15

ìļ´ëį°

-0.14

saldo

-0.14

Ð»ÑİÑĩÐ°

-0.14

mer

-0.14

Î¸Î±

-0.14

/apis

-0.14

POSITIVE LOGITS

azen

0.19

ziel

0.18

isch

0.17

ket

0.16

/Open

0.15

pled

0.15

PUR

0.15

bish

0.14

loha

0.14

çĽ´

0.14

Activations Density 0.023%

version numbers or version-related information

No Comments

No Known Activations