INDEX

Explanations

phrases related to social dynamics and behaviors, particularly those that highlight negative traits or conflicts within relationships

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

occo

-0.18

ilip

-0.15

iken

-0.14

izo

-0.14

ittings

-0.14

izr

-0.14

itti

-0.13

anine

-0.13

coon

-0.13

eel

-0.13

POSITIVE LOGITS

 types

0.18

 ìľłíĺķ

0.18

 troublesome

0.18

 personality

0.17

 toxic

0.17

aber

0.17

avr

0.17

 Types

0.16

vari

0.16

types

0.16

Activations Density 0.180%

phrases related to social dynamics and behaviors, particularly those that highlight negative traits or conflicts within relationships

No Comments

No Known Activations