INDEX

Explanations

references to academic journals and metrics related to research and publishing

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

acht

-0.16

-0.15

 Mall

-0.15

ainen

-0.15

à¸ªà¸ĩ

-0.14

uto

-0.14

 native

-0.14

ofs

-0.14

opp

-0.14

POSITIVE LOGITS

vsp

0.16

 Peer

0.15

è±Ĩ

0.14

 hÆ°á»Łng

0.14

 peer

0.14

æĬľ

0.14

bette

0.14

cratch

0.14

ovky

0.14

-peer

0.14

Activations Density 0.015%

references to academic journals and metrics related to research and publishing

No Comments

No Known Activations