INDEX

Explanations

keywords and identifiers related to programming and data structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

odynam

-0.14

edException

-0.14

WithEmail

-0.14

Ãłng

-0.14

 Marin

-0.14

instead

-0.13

á»©

-0.13

olta

-0.13

pha

-0.12

ird

-0.12

POSITIVE LOGITS

istrovstvÃŃ

0.16

evin

0.15

toy

0.13

onas

0.13

/Dk

0.13

commission

0.12

/INFO

0.12

nave

0.12

ierge

0.12

ÙİØ§ÙĦ

0.12

Activations Density 0.270%

keywords and identifiers related to programming and data structures

No Comments

No Known Activations