INDEX

Explanations

numerical data or statistics related to studies or claims

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

lu

-0.18

anc

-0.15

iel

-0.15

Î®

-0.14

 progress

-0.14

ling

-0.14

Î®Î½

-0.14

 Bilim

-0.14

POSITIVE LOGITS

ãĥ³ãĤ°ãĥ«

0.15

Ð³Ð¸

0.15

Pur

0.15

ASY

0.14

-transitional

0.14

à¤ľà¤°

0.14

unsch

0.14

ertz

0.14

.openConnection

0.13

Pap

0.13

Activations Density 0.033%

numerical data or statistics related to studies or claims

No Comments

No Known Activations