INDEX

Explanations

phrases involving specific articles and prepositions

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

issance

-0.15

 Shuttle

-0.15

 Wise

-0.15

ç§

-0.15

.examples

-0.14

.dtd

-0.14

 (!((

-0.14

edBy

-0.13

 Tavern

-0.13

ĮĢ

-0.13

POSITIVE LOGITS

 subsequ

0.18

_argv

0.16

erge

0.15

strar

0.15

anel

0.15

arg

0.15

uka

0.15

osg

0.15

 Antar

0.14

 Belt

0.14

Activations Density 0.066%

phrases involving specific articles and prepositions

No Comments

No Known Activations