INDEX

Explanations

elements related to geographic locations or specific measurements

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

izzle

-0.14

Cic

-0.14

 Zimmerman

-0.14

undo

-0.14

.ToDateTime

-0.14

éŀ

-0.14

EMA

-0.13

 Hast

-0.13

 Venez

-0.13

illusion

-0.13

POSITIVE LOGITS

 embr

0.15

 comp

0.14

itan

0.14

AF

0.14

 peripheral

0.14

 RoundedRectangle

0.14

itre

0.14

Cre

0.13

Cre

0.13

otine

0.13

Activations Density 0.013%

elements related to geographic locations or specific measurements

No Comments

No Known Activations