INDEX

Explanations

terms related to boxing techniques and actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

istrovstvÃŃ

-0.20

vig

-0.16

asca

-0.15

ë¢°

-0.15

iveau

-0.14

 mysl

-0.14

omorphic

-0.14

 Bark

-0.13

ingham

-0.13

vro

-0.13

POSITIVE LOGITS

 Warfare

0.15

 programming

0.15

 shades

0.14

azard

0.13

 inspiration

0.13

edu

0.13

 èĩ

0.13

.trade

0.13

Activations Density 0.005%

terms related to boxing techniques and actions

No Comments

No Known Activations