INDEX

Explanations

references to specific cultural institutions and locations in the context of art exhibitions

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

MMdd

-0.15

.nano

-0.15

liches

-0.14

åħĥ

-0.14

cial

-0.14

amburg

-0.14

çłģ

-0.14

.addValue

-0.13

ilo

-0.13

 Ð¸Ð¼Ñĥ

-0.13

POSITIVE LOGITS

idor

0.19

pie

0.16

SG

0.15

ĩ

0.15

IRA

0.15

Pie

0.15

pie

0.15

maal

0.14

 conse

0.14

xd

0.14

Activations Density 0.024%

references to specific cultural institutions and locations in the context of art exhibitions

No Comments

No Known Activations