INDEX

Explanations

references to art exhibitions and performances

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

Ãºc

-0.16

amas

-0.15

 hollow

-0.15

pawn

-0.15

Arch

-0.15

orum

-0.14

amarin

-0.14

Ð¼Ð°Ð³

-0.14

unes

-0.14

 hete

-0.14

POSITIVE LOGITS

 slot

0.15

 Brock

0.15

éĻĲå®ļ

0.14

 Slot

0.14

ÃŃo

0.14

Ear

0.14

åºľ

0.14

bedo

0.14

Decoration

0.13

Activations Density 0.057%

references to art exhibitions and performances

No Comments

No Known Activations