INDEX

Explanations

words related to management and executives

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

afari

-0.18

ils

-0.18

ics

-0.17

opot

-0.15

ovah

-0.14

 ÑĥÐ³Ð¾Ð´

-0.14

oras

-0.14

owing

-0.14

vac

-0.14

uddenly

-0.14

POSITIVE LOGITS

 partner

0.30

 Partner

0.27

 director

0.26

Partner

0.25

partner

0.25

 partners

0.24

 Partners

0.22

 directors

0.21

_partner

0.21

 Director

0.20

Activations Density 0.005%

words related to management and executives

No Comments

No Known Activations