INDEX

Explanations

phrases indicating leadership or being at the forefront within various sectors

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

ëŁī

-0.16

ilda

-0.15

ych

-0.15

ment

-0.14

 cloth

-0.14

USE

-0.13

pie

-0.13

gua

-0.13

culos

-0.13

-faced

-0.13

POSITIVE LOGITS

-edge

0.20

Escort

0.19

ache

0.16

0.15

kyt

0.15

resher

0.15

-flight

0.14

ãĥ³ãĥĨ

0.14

ivot

0.14

VertexAttrib

0.14

Activations Density 0.019%

phrases indicating leadership or being at the forefront within various sectors

No Comments

No Known Activations