INDEX

Explanations

references to specific geographic locations and wildlife conservation efforts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

buie

-0.18

 Gaut

-0.15

åľĪ

-0.15

asca

-0.15

 Lyons

-0.15

 Episodes

-0.15

 ÑĤÐ¾Ð²

-0.15

_CPU

-0.15

ooke

-0.15

 Ð½ÐµÐ¾Ð±

-0.14

POSITIVE LOGITS

 tribal

0.24

 Tribal

0.23

 Frontier

0.23

 tribes

0.22

Pas

0.22

 Afghan

0.18

 Afghanistan

0.18

Pas

0.18

tal

0.17

Tal

0.17

Activations Density 0.013%

references to specific geographic locations and wildlife conservation efforts

No Comments

No Known Activations