INDEX

Explanations

quantities associated with time or frequency

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

è²¬

-0.15

 Kerr

-0.14

outh

-0.14

bao

-0.14

riz

-0.14

 somew

-0.14

ideo

-0.14

Ø°Ø±

-0.13

ourg

-0.13

kus

-0.13

POSITIVE LOGITS

 alike

0.22

 Salon

0.16

DDL

0.15

ëĿ½

0.15

/etc

0.15

ivors

0.15

acle

0.14

.locals

0.14

 Haley

0.14

HLT

0.14

Activations Density 0.026%

quantities associated with time or frequency

No Comments

No Known Activations