INDEX

Explanations

references to algorithms and modeling processes in programming or machine learning contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

_rewrite

-0.14

Taj

-0.14

igor

-0.13

ango

-0.13

 patter

-0.13

het

-0.13

Ã¼lÃ¼

-0.13

OffsetTable

-0.13

Tor

-0.13

 pattern

-0.12

POSITIVE LOGITS

 boosting

0.26

 train

0.26

 RandomForest

0.26

 booster

0.24

.boost

0.24

.fit

0.24

 Boost

0.23

train

0.23

è¢ĭ

0.23

CV

0.23

Activations Density 0.029%

references to algorithms and modeling processes in programming or machine learning contexts

No Comments

No Known Activations