INDEX

Explanations

technical terminology and code structures related to programming and software development

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

 Shel

-0.16

itere

-0.16

isable

-0.14

idata

-0.14

ternet

-0.14

usher

-0.13

izable

-0.13

Lod

-0.13

rud

-0.13

odiac

-0.13

POSITIVE LOGITS

 muse

0.17

 Muse

0.15

arden

0.15

ucer

0.15

auer

0.15

endencies

0.14

andom

0.14

ende

0.14

íĽĪ

0.14

 Kong

0.14

Activations Density 0.051%

technical terminology and code structures related to programming and software development

No Comments

No Known Activations