INDEX

Explanations

URLs or pathway indicators in the text

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

å¤§å°ı

-0.15

 Bills

-0.14

addock

-0.14

aug

-0.14

semble

-0.14

angu

-0.14

beit

-0.14

etes

-0.13

 Stanton

-0.13

 conscience

-0.13

POSITIVE LOGITS

cents

0.16

.scalablytyped

0.15

 Scho

0.15

anik

0.14

ody

0.13

imitives

0.13

Demand

0.13

chs

0.13

se

0.13

Activations Density 0.001%

URLs or pathway indicators in the text

No Comments

No Known Activations