INDEX

Explanations

references to actors and acting

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

seo

-0.20

isseur

-0.17

mey

-0.16

 actionTypes

-0.15

Mocks

-0.15

UNT

-0.15

atics

-0.15

Ð¾Ð·Ð°

-0.15

thane

-0.14

 luáºŃn

-0.14

POSITIVE LOGITS

rel

0.15

ÏĥÎºÎµ

0.15

/model

0.15

inox

0.15

ëĪĦ

0.15

-NLS

0.14

 veter

0.13

alar

0.13

ValuePair

0.13

ref

0.13

Activations Density 0.021%

references to actors and acting

No Comments

No Known Activations