INDEX

Explanations

keywords and phrases indicating significance or importance in diverse contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

ikon

-0.15

axon

-0.15

á»ĭnh

-0.15

deck

-0.15

 Binder

-0.14

erde

-0.14

ÏĮÏĤ

-0.14

ãĥĩãĤ£ãĤ¢

-0.14

 fitte

-0.14

rek

-0.14

POSITIVE LOGITS

erosis

0.17

iten

0.16

cit

0.16

aar

0.15

Affected

0.15

ennis

0.15

COD

0.14

ëĭ´

0.14

 Pref

0.14

.encoding

0.14

Activations Density 0.019%

keywords and phrases indicating significance or importance in diverse contexts

No Comments

No Known Activations