INDEX

Explanations

negations and negative statements about various subjects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

Ã¼b

-0.15

 partially

-0.15

-0.14

Ã¦k

-0.14

Î»Î»Î·

-0.14

osg

-0.14

esine

-0.14

still

-0.13

sher

-0.13

POSITIVE LOGITS

 necessarily

0.37

 exclusively

0.26

 exclusive

0.24

 alone

0.23

 solely

0.23

ecessarily

0.19

-exclusive

0.19

 sole

0.19

sole

0.18

å¿ħ

0.18

Activations Density 0.293%

negations and negative statements about various subjects

No Comments

No Known Activations