INDEX

Explanations

possessive forms or phrases indicating ownership

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

umes

-0.16

gel

-0.15

-0.14

uzzi

-0.14

lessly

-0.14

oc

-0.14

otal

-0.14

 rarity

-0.14

 karak

-0.14

etsk

-0.14

POSITIVE LOGITS

 microtime

0.17

-eye

0.16

raith

0.16

¨ë¶Ģ

0.15

enga

0.15

ÂĢÂĻ

0.15

vester

0.15

rtl

0.15

vard

0.15

GetMethod

0.14

Activations Density 0.124%

possessive forms or phrases indicating ownership

No Comments

No Known Activations