INDEX

Explanations

words associated with managerial or leadership roles

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

afari

-0.19

-0.17

ils

-0.16

à¸¤

-0.15

andin

-0.15

friendly

-0.15

ics

-0.15

 ÑĥÐ³Ð¾Ð´

-0.15

POSITIVE LOGITS

 director

0.30

 Director

0.26

 directors

0.24

 Directors

0.23

 partner

0.23

director

0.23

 Partner

0.22

Director

0.22

irector

0.20

partner

0.19

Activations Density 0.004%

words associated with managerial or leadership roles

No Comments

No Known Activations