INDEX

Explanations

references to physical activity and exercise

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

lak

-0.16

DJ

-0.15

ofilm

-0.15

wash

-0.14

DJ

-0.14

chod

-0.14

doch

-0.14

onden

-0.14

ise

-0.14

Dj

-0.14

POSITIVE LOGITS

 exercise

0.19

/stretch

0.18

nas

0.18

 fitness

0.18

gym

0.18

_THROW

0.16

exercise

0.16

Exercise

0.16

 exerc

0.15

 Fitness

0.15

Activations Density 0.128%

references to physical activity and exercise

No Comments

No Known Activations