INDEX

Explanations

references to specific model names or products, particularly in technology

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

igel

-0.17

.mozilla

-0.15

enÃ§a

-0.15

strup

-0.15

asa

-0.15

åĩºåĵģ

-0.14

ylene

-0.14

 dirent

-0.14

ifr

-0.14

upos

-0.14

POSITIVE LOGITS

lag

0.16

ehr

0.16

arma

0.15

 Sesso

0.15

Int

0.14

åĬĽ

0.14

amps

0.14

Sie

0.14

/Common

0.14

ardy

0.14

Activations Density 0.004%

references to specific model names or products, particularly in technology

No Comments

No Known Activations