INDEX

Explanations

terms related to washing and cleaning tasks or items

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

ecies

-0.19

antly

-0.17

-0.16

ziej

-0.16

AMERA

-0.15

_python

-0.15

ateurs

-0.15

opian

-0.15

ept

-0.15

iller

-0.14

POSITIVE LOGITS

room

0.26

inton

0.26

bas

0.25

rooms

0.24

cloth

0.23

out

0.23

ateria

0.21

ingt

0.21

clo

0.21

oe

0.20

Activations Density 0.016%

terms related to washing and cleaning tasks or items

No Comments

No Known Activations