INDEX

Explanations

concepts related to authority, obedience, and governance

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

ize

-0.18

hard

-0.15

adem

-0.15

.fi

-0.14

atics

-0.14

_transient

-0.14

Ð·Ð½Ð°ÑĩÐ°

-0.13

Ã¥l

-0.13

POSITIVE LOGITS

asaki

0.15

xiv

0.15

Ã¼hl

0.15

dust

0.14

Watcher

0.14

eÄį

0.14

ÅĻeb

0.14

etik

0.13

ãĥ³ãĥģ

0.13

ÛĢ

0.13

Activations Density 0.675%

concepts related to authority, obedience, and governance

No Comments

No Known Activations