INDEX

Explanations

references and terminologies related to downloads and file availability

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

-0.21

’

-0.21

Dra

-0.18

Neu

-0.15

kab

-0.15

ov

-0.15

umin

-0.15

MethodInfo

-0.15

iet

-0.15

POSITIVE LOGITS

osu

0.17

ifter

0.16

Miz

0.15

"display

0.15

ë¦¬ìķĦ

0.14

ìĭĿ

0.14

izu

0.14

ÏĢÎ¿Ïį

0.14

asin

0.13

amba

0.13

Activations Density 0.293%

references and terminologies related to downloads and file availability

No Comments

No Known Activations