INDEX

Explanations

references to scientific studies or publications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

 Ð°ÐºÑĤÑĥ

-0.14

roll

-0.14

 Brooks

-0.13

 newSize

-0.13

Bis

-0.13

planet

-0.13

(nameof

-0.13

ensi

-0.13

rum

-0.13

ave

-0.13

POSITIVE LOGITS

eds

0.16

ipse

0.15

Ìģt

0.15

disposing

0.15

 Sesso

0.14

endcode

0.14

 paran

0.13

Intialized

0.13

+:+

0.13

Activations Density 0.049%

references to scientific studies or publications

No Comments

No Known Activations