INDEX

Explanations

references to governmental actions and societal issues

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

-0.15

 Pillow

-0.14

 spanish

-0.14

DAQ

-0.14

BOR

-0.14

 GOODMAN

-0.14

amina

-0.14

 Hispanic

-0.14

 pillow

-0.14

uslim

-0.14

POSITIVE LOGITS

 Popular

0.20

 Integral

0.18

 Schultz

0.17

 Rousse

0.16

 Guar

0.16

 integral

0.16

SIN

0.15

 guar

0.15

FML

0.15

 Interior

0.15

Activations Density 0.032%

references to governmental actions and societal issues

No Comments

No Known Activations