INDEX

Explanations

references to specific data structures and their characteristics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

ninger

-0.17

 thÃº

-0.14

wick

-0.14

ä¼ı

-0.14

jspx

-0.14

.localized

-0.14

asso

-0.14

ãĥĢãĤ¤

-0.14

ÙĴØ³

-0.14

ÑĤÐµÑĢÐ½

-0.14

POSITIVE LOGITS

/static

0.18

ded

0.16

 mode

0.16

_RDONLY

0.15

readonly

0.15

 Mode

0.15

 cold

0.15

 immutable

0.15

DC

0.15

FB

0.14

Activations Density 0.147%

references to specific data structures and their characteristics

No Comments

No Known Activations