INDEX

Explanations

statements or claims about surveillance and authority

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

obus

-0.17

zburg

-0.17

uis

-0.16

tte

-0.15

nave

-0.15

Slinky

-0.15

ĩĮ

-0.15

erland

-0.15

olds

-0.15

endale

-0.15

POSITIVE LOGITS

 Cassidy

0.16

 Sesso

0.15

 Pacific

0.14

unch

0.14

 íĥ

0.14

Tic

0.14

 Casinos

0.13

ument

0.13

(http

0.13

DataSet

0.13

Activations Density 0.201%

statements or claims about surveillance and authority

No Comments

No Known Activations