INDEX

Explanations

references to search functions and navigation within documents

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

-0.16

-0.15

Ð¼Ð¾ÑĤÑĢ

-0.14

burg

-0.14

agne

-0.14

rove

-0.14

ÐµÐ»Ðµ

-0.14

 Hind

-0.14

iola

-0.14

 Houses

-0.14

POSITIVE LOGITS

getDisplay

0.14

ãĥ©ãĤ¹

0.14

rapped

0.14

ÃŃf

0.14

.Typed

0.13

idden

0.13

Ã»t

0.13

Î´ÎŃ

0.13

Dear

0.13

elli

0.13

Activations Density 0.001%

references to search functions and navigation within documents

No Comments

No Known Activations