INDEX

Explanations

references to specific geographic locations and entities related to governance and societal structure

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

ulan

-0.16

oni

-0.16

bins

-0.15

znik

-0.15

ÐµÐ¼Ð°

-0.15

.keyword

-0.15

onas

-0.15

 Charg

-0.15

onen

-0.14

ourke

-0.14

POSITIVE LOGITS

isz

0.15

à¸Ļà¸Ń

0.15

DRV

0.15

ozem

0.15

sumer

0.14

anth

0.14

chop

0.14

è¡Ĩ

0.14

 lookahead

0.14

ObjectId

0.14

Activations Density 1.164%

references to specific geographic locations and entities related to governance and societal structure

No Comments

No Known Activations