INDEX

Explanations

terms related to fractures and injuries, particularly of bones

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

 impe

-0.16

(contents

-0.16

ourg

-0.15

anship

-0.15

cher

-0.15

 Pier

-0.14

 backed

-0.14

bson

-0.14

stor

-0.14

 Buchanan

-0.14

POSITIVE LOGITS

 bones

0.58

 bone

0.57

 Bone

0.50

bones

0.49

Bone

0.49

 Bones

0.48

bone

0.47

éª¨

0.46

 xÆ°Æ¡ng

0.36

 skeleton

0.33

Activations Density 0.055%

terms related to fractures and injuries, particularly of bones

No Comments

No Known Activations