INDEX

Explanations

numerical references and formatting

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

orta

-0.15

VK

-0.15

plier

-0.14

ptom

-0.14

aller

-0.14

 zase

-0.14

vh

-0.13

getElement

-0.13

Î»Î±

-0.13

 Weekend

-0.13

POSITIVE LOGITS

ãĤīãģĦ

0.16

olleyError

0.15

.updateDynamic

0.15

pun

0.15

ìłķë¶Ģ

0.15

">//

0.15

 bound

0.14

aÅ¾d

0.14

SupportedContent

0.14

Activations Density 0.093%

numerical references and formatting

No Comments

No Known Activations