INDEX

Explanations

terms related to imaging and film technology

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

coil

-0.14

ollision

-0.14

 adult

-0.14

obili

-0.14

 regional

-0.14

 Collision

-0.13

(logger

-0.13

ãģıãģł

-0.13

_sphere

-0.13

.Parse

-0.13

POSITIVE LOGITS

Kod

0.25

 film

0.25

 Film

0.24

film

0.24

Film

0.24

 exposures

0.23

 Ð¿Ð»ÐµÐ½

0.21

 exposure

0.20

 Ð¿ÑĢÐ¾ÑıÐ²

0.19

 Exposure

0.19

Activations Density 0.049%

terms related to imaging and film technology

No Comments

No Known Activations