INDEX

Explanations

terms related to prisoners of war and their status

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

abh

-0.15

ovit

-0.15

EMENT

-0.15

ite

-0.14

çłģ

-0.14

ãĤĵ

-0.14

 Wheels

-0.14

lund

-0.14

Ä°R

-0.14

POSITIVE LOGITS

ouser

0.15

StateManager

0.15

rous

0.15

bounds

0.14

ouro

0.14

Ð½Ð¾Ð¿

0.14

Sie

0.13

unar

0.13

etrics

0.13

ÄĽÅ¾

0.13

Activations Density 0.023%

terms related to prisoners of war and their status

No Comments

No Known Activations