INDEX

Explanations

terms associated with academic titles and positions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

ĥĿ

-0.16

ycl

-0.16

Specifier

-0.16

Î®

-0.15

acher

-0.15

 èµ·

-0.15

lien

-0.15

.AppSettings

-0.14

 Crossing

-0.14

 serialVersionUID

-0.14

POSITIVE LOGITS

ion

0.16

 Middleton

0.16

ARIO

0.15

ocks

0.15

eteria

0.15

Gus

0.14

AYOUT

0.14

mentor

0.14

ario

0.14

kb

0.14

Activations Density 0.003%

terms associated with academic titles and positions

No Comments

No Known Activations