INDEX

Explanations

proper nouns and specific locations

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

Cri

-0.15

 Bret

-0.14

 ontvangst

-0.14

ingo

-0.14

 inert

-0.14

 Cobb

-0.14

 Corm

-0.14

 Dexter

-0.13

elo

-0.13

POSITIVE LOGITS

akov

0.15

endar

0.15

agini

0.14

ecies

0.14

intros

0.14

lingen

0.14

isses

0.14

 Twig

0.14

 lesb

0.14

idual

0.14

Activations Density 0.003%

proper nouns and specific locations

No Comments

No Known Activations