INDEX

Explanations

phrases that denote possession or ownership

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

reur

-0.17

kul

-0.14

vÃŃ

-0.14

ABI

-0.14

éĤ

-0.14

 Bliss

-0.14

 Griffin

-0.14

Ð°ÑĢÐ¾Ð²

-0.14

£

-0.13

cin

-0.13

POSITIVE LOGITS

Äįet

0.17

lash

0.16

Î³Î¿Ïģ

0.15

leen

0.15

ÄįÃ¡st

0.14

wap

0.14

PEED

0.14

ìĹŃ

0.14

ugi

0.13

Activations Density 0.202%

phrases that denote possession or ownership

No Comments

No Known Activations