INDEX

Explanations

various character encoding formats

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

ilit

-0.17

 Roman

-0.15

Ã©ru

-0.15

ita

-0.15

nr

-0.14

cab

-0.14

dao

-0.14

addock

-0.14

 pole

-0.14

Roman

-0.14

POSITIVE LOGITS

Bindable

0.15

ãĥ¼ãĥĲ

0.15

.bc

0.15

\Migrations

0.15

uster

0.14

ÙħÙĪØ¯

0.14

_EXPR

0.14

shima

0.14

ãĥ¼ãĥį

0.13

Activations Density 0.000%

various character encoding formats

No Comments

No Known Activations