INDEX

Explanations

references to individuals' accomplishments and professional roles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

opsis

-0.17

instrument

-0.15

Ã´i

-0.15

duc

-0.15

ÅĽli

-0.14

agraph

-0.14

Î¼Î±ÏĦÎ¿

-0.14

 ìŀĳìĦ±

-0.14

 instrument

-0.14

ijkstra

-0.14

POSITIVE LOGITS

 appearances

0.24

 chamber

0.23

 solo

0.20

rec

0.20

 appearing

0.20

Wig

0.19

duo

0.19

 prem

0.19

 Chamber

0.19

 engagements

0.19

Activations Density 0.019%

references to individuals' accomplishments and professional roles

No Comments

No Known Activations

references to individuals' accomplishments and professional roles

No Comments

No Known Activations