INDEX

Explanations

references to specific locations and event details related to a venue

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

owitz

-0.16

 Newport

-0.16

mÃŃn

-0.15

uche

-0.15

olik

-0.15

Å¥

-0.14

ANTE

-0.14

à¸Ńà¸Ķ

-0.14

exion

-0.14

erokee

-0.14

POSITIVE LOGITS

 Tampa

0.38

 Tamil

0.22

Bay

0.19

 Buccaneers

0.19

 Osaka

0.19

 Everton

0.18

Bay

0.18

 Chennai

0.18

éĺª

0.17

Activations Density 0.049%

references to specific locations and event details related to a venue

No Comments

No Known Activations