INDEX

Explanations

references to the journal "Nature."

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

piel

-0.15

 ===>

-0.15

udeau

-0.15

onto

-0.15

oron

-0.15

pii

-0.14

terior

-0.14

ÐµÐ¼Ñĥ

-0.14

aday

-0.14

 Mercy

-0.14

POSITIVE LOGITS

 feed

0.15

 Hose

0.15

æ©

0.15

otten

0.14

cular

0.14

 liá»ĩu

0.14

gal

0.14

kad

0.14

agas

0.14

Activations Density 0.007%

references to the journal "Nature."

No Comments

No Known Activations