INDEX

Explanations

phrases related to horse racing and competition

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

igner

-0.17

anio

-0.16

zap

-0.15

 Å¼

-0.14

 sluts

-0.13

 civilian

-0.13

_VM

-0.13

 Ð±Ñĥ

-0.13

igers

-0.13

POSITIVE LOGITS

 Previous

0.14

Ã¡o

0.14

 Hansen

0.14

 fitness

0.14

aky

0.14

±

0.14

 FITNESS

0.14

 backers

0.14

 fractional

0.14

 progressive

0.14

Activations Density 0.028%

phrases related to horse racing and competition

No Comments

No Known Activations