INDEX

Explanations

phrases that include the word "with" indicating relationships or connections

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

CJK

-0.15

 pokoj

-0.15

apg

-0.15

 OnTrigger

-0.15

cko

-0.14

«a

-0.14

kili

-0.14

 Salad

-0.14

_Parms

-0.14

bÃŃr

-0.14

POSITIVE LOGITS

0.17

other

0.16

ellan

0.15

...

0.15

 additional

0.15

an

0.14

 inne

0.14

an

0.14

 Martin

0.14

 Golden

0.14

Activations Density 0.047%

phrases that include the word "with" indicating relationships or connections

No Comments

No Known Activations