INDEX

Explanations

elements related to data collection and documentation processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

Hav

-0.17

Loy

-0.14

 Hoffman

-0.14

ser

-0.13

 Wolff

-0.13

anova

-0.13

ire

-0.13

rift

-0.13

cast

-0.13

.ssl

-0.13

POSITIVE LOGITS

 survey

0.37

 Survey

0.35

survey

0.34

Survey

0.32

urvey

0.31

 surveys

0.30

 surveyed

0.29

_survey

0.28

 cada

0.24

 CORS

0.24

Activations Density 0.034%

elements related to data collection and documentation processes

No Comments

No Known Activations