INDEX

Explanations

technical terms and references 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

onom

-0.17

ufe

-0.16

ÑĤÑĢÐ°

-0.15

 increment

-0.14

ographer

-0.14

ert

-0.14

ster

-0.14

aring

-0.14

 Helm

-0.13

ØºØ±Ø§Ùģ

-0.13

POSITIVE LOGITS

sWith

0.15

nodoc

0.14

mitt

0.14

_,,

0.14

nicos

0.14

RTL

0.14

rapper

0.14

 getInt

0.14

à¸Ĺà¸Ńà¸ĩ

0.13

ÑĭÑĪÐ»ÐµÐ½

0.13

Activations Density 0.375%

technical terms and references related to programming and software development

No Comments

No Known Activations