INDEX

Explanations

references to various associations and organizations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

enti

-0.16

elman

-0.15

å¸ĸ

-0.15

StrictEqual

-0.15

bine

-0.15

osi

-0.15

Ø³Ø§Ø¨

-0.15

wu

-0.14

 Ð²ÑģÑĤ

-0.14

ncy

-0.14

POSITIVE LOGITS

 Chiefs

0.16

utzer

0.15

 chiefs

0.14

 Casual

0.14

olor

0.14

ivre

0.14

 Feder

0.14

 chief

0.14

 incur

0.13

days

0.13

Activations Density 0.020%

references to various associations and organizations

No Comments

No Known Activations