INDEX

Explanations

phrases that convey quality or excellence in products or ideas

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

vailability

-0.15

anel

-0.15

-0.14

Åĵ

-0.14

ì°¬

-0.14

LOB

-0.13

ober

-0.13

 ÑĢÐ°Ð·Ñĸ

-0.13

herit

-0.13

urette

-0.13

POSITIVE LOGITS

éģĶ

0.16

cka

0.16

lei

0.14

obuf

0.14

jvu

0.14

/hash

0.14

è¾¾

0.14

 indice

0.14

æļ´

0.14

aw

0.14

Activations Density 0.008%

phrases that convey quality or excellence in products or ideas

No Comments

No Known Activations