INDEX

Explanations

technical terms and operations related to programming and data management

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

setId

-0.16

anni

-0.15

isis

-0.15

subjects

-0.14

utschen

-0.14

 Dominion

-0.14

 Bounds

-0.13

arin

-0.13

ze

-0.13

 setFrame

-0.13

POSITIVE LOGITS

bare

0.17

rawler

0.16

.lu

0.15

Ø±Ø²

0.15

 createAction

0.15

ikon

0.15

.CREATED

0.14

lu

0.14

ROC

0.14

lund

0.14

Activations Density 0.031%

technical terms and operations related to programming and data management

No Comments

No Known Activations