INDEX

Explanations

references to scientific concepts and terminology related to various fields

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

inton

-0.16

atron

-0.16

ãĥ³ãĥĩ

-0.15

Ð¸ÑģÑĮ

-0.15

WISE

-0.14

emark

-0.14

oto

-0.14

ãĤ£

-0.14

ishing

-0.13

à¹ĥà¸ª

-0.13

POSITIVE LOGITS

 alongside

0.16

 ÙĪÙģÙĬ

0.16

UpInside

0.15

tracts

0.15

Normalization

0.14

 èĻ

0.14

_mE

0.14

dlg

0.14

sled

0.14

hower

0.14

Activations Density 0.290%

references to scientific concepts and terminology related to various fields

No Comments

No Known Activations