INDEX

Explanations

variations of the word "practice."

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

duk

-0.16

ilin

-0.16

uyo

-0.15

 Practical

-0.15

alaria

-0.14

à¸´à¸ķà¸¢

-0.14

ptest

-0.14

crm

-0.14

ftar

-0.14

quest

-0.14

POSITIVE LOGITS

aus

0.17

ahl

0.16

andes

0.16

MBOL

0.15

åªĴ

0.14

 Bern

0.14

enburg

0.13

dirty

0.13

åłĤ

0.13

Serializable

0.13

Activations Density 0.020%

variations of the word "practice."

No Comments

No Known Activations