INDEX

Explanations

mentions of the term "General" or references to "General Electric" and related entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

ors

-0.17

 generic

-0.16

uet

-0.15

Ã¡k

-0.15

 generally

-0.15

phere

-0.15

ulously

-0.15

oug

-0.15

ogenic

-0.14

ante

-0.14

POSITIVE LOGITS

-purpose

0.28

ised

0.27

izations

0.25

isations

0.25

ized

0.21

-ÑĤÐ¾

0.21

 Motors

0.21

izable

0.20

ization

0.20

iss

0.20

Activations Density 0.018%

mentions of the term "General" or references to "General Electric" and related entities

No Comments

No Known Activations