INDEX

Explanations

terminologies and phrases related to social relationships

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

ctp

-0.13

mk

-0.13

 Alphabet

-0.13

emed

-0.13

elm

-0.13

 stoi

-0.13

alm

-0.13

quote

-0.12

 Logic

-0.12

POSITIVE LOGITS

 usage

0.30

usage

0.28

 referring

0.27

 Usage

0.27

 applied

0.27

 terms

0.26

Usage

0.26

 interchangeable

0.25

 describing

0.25

 term

0.24

Activations Density 0.389%

terminologies and phrases related to social relationships

No Comments

No Known Activations