INDEX

Explanations

terms related to technology and hardware in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

idis

-0.15

rzy

-0.15

Ð²ÑĸÐ»ÑĮ

-0.14

/member

-0.14

_ENUM

-0.14

ivable

-0.14

otime

-0.14

Å¾ÃŃ

-0.13

/job

-0.13

POSIT

-0.13

POSITIVE LOGITS

 physical

0.21

 Physical

0.19

physical

0.18

 fÃŃs

0.18

Physical

0.17

æĸ¹éĿ¢

0.16

iki

0.16

 aspect

0.15

 physically

0.15

ourke

0.15

Activations Density 0.349%

terms related to technology and hardware in various contexts

No Comments

No Known Activations