INDEX

Explanations

specific names and references related to popular culture and notable figures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

lant

-0.16

à¹ĥà¸Ī

-0.16

azen

-0.16

ĥĿ

-0.15

anj

-0.14

latin

-0.14

oca

-0.14

 Casinos

-0.14

ewire

-0.14

ErrorHandler

-0.14

POSITIVE LOGITS

ABS

0.19

sha

0.16

smith

0.16

 Levine

0.15

 Morrison

0.15

ubu

0.15

iku

0.14

ilit

0.14

tic

0.14

ABC

0.13

Activations Density 0.071%

specific names and references related to popular culture and notable figures

No Comments

No Known Activations