INDEX

Explanations

references to injuries, scars, and medical conditions related to physical trauma

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

 Ð³ÑĢÐ¾Ð¼

-0.16

 jaws

-0.15

 skeletons

-0.15

 ìļĶ

-0.15

 hÃ£

-0.14

ÅŁk

-0.14

ulkan

-0.14

 skulls

-0.14

 barrels

-0.14

POSITIVE LOGITS

 cuts

0.40

 wounds

0.34

 marks

0.34

 wound

0.33

 burns

0.29

 welt

0.28

 scratches

0.28

marks

0.28

 abras

0.28

 scars

0.28

Activations Density 0.196%

references to injuries, scars, and medical conditions related to physical trauma

No Comments

No Known Activations