INDEX

Explanations

terms associated with dependency and abuse in the context of substances or behaviors

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

vak

-0.17

Lev

-0.15

apt

-0.14

 prompt

-0.14

ãĥªãĥ¼ãĤº

-0.14

 stan

-0.13

_simps

-0.13

usher

-0.13

 âĨĶ

-0.13

 recession

-0.13

POSITIVE LOGITS

edList

0.17

andÄ±r

0.14

HELL

0.14

exo

0.14

 Floor

0.14

$_[

0.13

oned

0.13

epad

0.13

clave

0.13

Fc

0.13

Activations Density 1.628%

terms associated with dependency and abuse in the context of substances or behaviors

No Comments

No Known Activations