INDEX

Explanations

instances of being compelled or obligated to act in a certain way

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

dt

-0.17

ven

-0.16

nde

-0.15

Ð°Ð½ÑģÐ¸

-0.14

kova

-0.14

ç³»

-0.14

ãģŁãĤī

-0.14

 Freed

-0.14

reo

-0.14

ssel

-0.14

POSITIVE LOGITS

 into

0.25

 onto

0.23

into

0.22

forced

0.21

 Forced

0.20

 forced

0.19

onto

0.19

_into

0.18

ache

0.18

berger

0.17

Activations Density 0.043%

instances of being compelled or obligated to act in a certain way

No Comments

No Known Activations