INDEX

Explanations

specific structural elements in text, likely focusing on punctuation and conjunctions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

 Cargo

-0.18

 personally

-0.15

avan

-0.15

ä¸

-0.14

 Markus

-0.14

clar

-0.14

 Viewing

-0.14

atz

-0.14

 cargo

-0.14

 Stuart

-0.14

POSITIVE LOGITS

tees

0.18

/xml

0.15

.assets

0.15

(~(

0.15

tee

0.15

ood

0.15

tank

0.15

ëĺĲ

0.15

0.14

Activations Density 0.000%

specific structural elements in text, likely focusing on punctuation and conjunctions

No Comments

No Known Activations