INDEX

Explanations

negative sentiments and experiences related to people and their behavior

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

eteria

-0.19

ibold

-0.16

ovice

-0.16

yonel

-0.16

etto

-0.15

_AA

-0.15

¶Į

-0.15

áº¿t

-0.15

owi

-0.15

onya

-0.14

POSITIVE LOGITS

 mean

0.30

 rude

0.28

 Mean

0.27

 abrasive

0.27

mean

0.26

alo

0.25

 comb

0.25

 judgment

0.23

ob

0.23

 confront

0.22

Activations Density 0.240%

negative sentiments and experiences related to people and their behavior

No Comments

No Known Activations