INDEX

Explanations

references to database configuration and manipulation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

Î³Î³ÎµÎ»

-0.18

sl

-0.15

der

-0.14

.MOUSE

-0.14

vet

-0.14

nett

-0.14

athers

-0.14

lip

-0.14

angen

-0.13

avy

-0.13

POSITIVE LOGITS

 name

0.21

name

0.19

åĲįç§°

0.18

 ìĿ´ë¦Ħ

0.18

 created

0.18

åĲį

0.17

 names

0.17

èħ

0.16

 named

0.16

NAME

0.16

Activations Density 0.050%

references to database configuration and manipulation

No Comments

No Known Activations