INDEX

Explanations

technical references and codes related to data processing or programming

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

ves

-0.15

-0.14

bow

-0.14

nun

-0.13

ÙĨØ§Ùħ

-0.13

iska

-0.13

Ð¾ÑĩÐ½Ð¾Ð¹

-0.13

ych

-0.13

Ã¥

-0.13

RICT

-0.13

POSITIVE LOGITS

fabs

0.15

ycop

0.14

.getSeconds

0.14

eah

0.14

æ²»

0.13

_codegen

0.13

ëĳĺ

0.13

ÙĪØ³ÛĮ

0.13

-'.$

0.13

 AUTHORS

0.13

Activations Density 0.956%

technical references and codes related to data processing or programming

No Comments

No Known Activations