INDEX

Explanations

numeric references and data related to individuals, particularly in genealogical or historical contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

udget

-0.16

.webkit

-0.15

ogie

-0.14

UILTIN

-0.14

Prime

-0.14

à¤¾à¤ªà¤¨

-0.14

fou

-0.13

ells

-0.13

 NSLocalizedString

-0.13

ivan

-0.13

POSITIVE LOGITS

ynet

0.16

orney

0.15

\Mapping

0.15

illes

0.15

ÑĥÐ½Ð´

0.15

ajes

0.14

aut

0.14

avn

0.14

pag

0.14

Activations Density 0.055%

numeric references and data related to individuals, particularly in genealogical or historical contexts

No Comments

No Known Activations