INDEX

Explanations

technical terms and functional words related to programming or data processing

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

 Beacon

-0.16

Ð¸ÑĤÑĭ

-0.15

_portal

-0.14

 moderation

-0.14

 Auditor

-0.14

engo

-0.14

atorial

-0.14

Bundle

-0.13

bud

-0.13

ÑĥÐ²Ð°

-0.13

POSITIVE LOGITS

Pav

0.16

leigh

0.16

vant

0.15

agt

0.15

Pad

0.15

iglia

0.14

 Shim

0.14

 Lans

0.14

 ÄĮer

0.14

Pad

0.14

Activations Density 0.013%

technical terms and functional words related to programming or data processing

No Comments

No Known Activations