INDEX

Explanations

references to academic publications or studies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

ses

-0.17

onda

-0.15

alo

-0.15

ecta

-0.15

atics

-0.15

rais

-0.15

atic

-0.14

olia

-0.14

 Shock

-0.14

 tactical

-0.14

POSITIVE LOGITS

jsc

0.15

mund

0.14

ulous

0.14

 contributing

0.14

eut

0.14

 ÐĵÑĢÐ¸Ð³Ð¾ÑĢ

0.14

ìĤ¬ì§Ģ

0.14

yte

0.14

ä¸įè¿ĩ

0.14

Activations Density 0.029%

references to academic publications or studies

No Comments

No Known Activations