INDEX

Explanations

numerical values and related data

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

osta

-0.17

-0.15

ulty

-0.15

oron

-0.15

ADF

-0.14

 æĿ¾

-0.14

ë¹ĦìĬ¤

-0.14

xef

-0.14

ilis

-0.14

Ú©Ø§

-0.14

POSITIVE LOGITS

aho

0.18

 Herbert

0.15

AAA

0.15

æĲ

0.15

 Electric

0.15

pek

0.15

ettes

0.14

ego

0.14

¼

0.14

Khu

0.14

Activations Density 0.017%

numerical values and related data

No Comments

No Known Activations