INDEX

Explanations

HTML navigation elements and structure

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

ãĥ¼ãĥĢ

-0.15

æķ·

-0.15

è²

-0.14

avan

-0.14

mann

-0.14

kir

-0.14

aven

-0.14

pository

-0.14

Å¼e

-0.13

 ä¿Ŀ

-0.13

POSITIVE LOGITS

 ninh

0.16

ahl

0.15

Ã¼c

0.15

 hacks

0.14

 Printable

0.14

amel

0.14

earer

0.14

iant

0.14

uce

0.13

isÃŃ

0.13

Activations Density 0.006%

HTML navigation elements and structure

No Comments

No Known Activations