INDEX

Explanations

references to investigations or studies related to technology and health

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

ifold

-0.17

 forg

-0.14

orial

-0.14

cai

-0.14

orp

-0.14

.tokens

-0.14

 pseud

-0.14

krv

-0.13

Ø§ÙħÙĦ

-0.13

hive

-0.13

POSITIVE LOGITS

 intended

0.19

 unrelated

0.17

ear

0.17

åİŁæľ¬

0.17

 originally

0.16

agu

0.16

 meant

0.15

 urÄį

0.15

ennon

0.15

 designed

0.15

Activations Density 0.241%

references to investigations or studies related to technology and health

No Comments

No Known Activations

references to investigations or studies related to technology and health

No Comments

No Known Activations