INDEX

Explanations

references to spatial positioning or directions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

/copyleft

-0.15

idue

-0.14

AT

-0.14

egend

-0.14

.AddComponent

-0.13

 Ã§Ä±kar

-0.13

uevo

-0.13

esus

-0.13

Cyr

-0.13

usercontent

-0.13

POSITIVE LOGITS

 RELATED

0.15

 signalling

0.14

passport

0.14

vÃ¡

0.13

leck

0.13

(reinterpret

0.13

ainless

0.13

ehler

0.13

uintptr

0.13

razione

0.13

Activations Density 0.007%

references to spatial positioning or directions

No Comments

No Known Activations