INDEX

Explanations

phrases related to injuries and medical conditions resulting from accidents

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

uet

-0.16

neau

-0.15

 piger

-0.14

_IL

-0.14

unchecked

-0.14

Ãªm

-0.14

 bankrupt

-0.13

Ð¾ÑĢÐ°Ð·

-0.13

 spoon

-0.13

POSITIVE LOGITS

 injuries

0.27

juries

0.21

 sustained

0.21

damage

0.20

 injury

0.20

 Injury

0.18

 damage

0.18

 wounds

0.16

 minor

0.16

ä¼¤

0.16

Activations Density 0.119%

phrases related to injuries and medical conditions resulting from accidents

No Comments

No Known Activations