INDEX

Explanations

key technical terms or phrases related to performance and function in various 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

rate

-0.16

aney

-0.16

ucker

-0.15

zi

-0.14

Aw

-0.14

ster

-0.14

uto

-0.14

Tower

-0.14

ÑĤÑĮ

-0.14

estro

-0.14

POSITIVE LOGITS

 Ellen

0.17

eneg

0.17

elsen

0.16

Ã©lÃ©

0.16

OLE

0.15

ell

0.15

ERE

0.15

dej

0.15

ellipsis

0.15

getElement

0.15

Activations Density 0.051%

key technical terms or phrases related to performance and function in various contexts

No Comments

No Known Activations