INDEX

Explanations

phrases indicating existence and presence of objects or people

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

oko

-0.18

Ø´ÙĪØ±

-0.16

essel

-0.15

á»ħ

-0.15

 mall

-0.15

XP

-0.14

 Clayton

-0.14

okies

-0.13

angs

-0.13

æŀľ

-0.13

POSITIVE LOGITS

 themselves

0.16

ãĥĲãĤ¤

0.15

wald

0.14

 WaitForSeconds

0.14

vine

0.14

ÑĤÑİ

0.14

ìĤ¬ìĿ´

0.14

Î¹Î»Î¿

0.13

 ourselves

0.13

 Trap

0.13

Activations Density 1.012%

phrases indicating existence and presence of objects or people

No Comments

No Known Activations