INDEX

Explanations

phrases related to power dynamics and authority within societal and educational contexts

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

.ef

-0.16

Ax

-0.14

 quietly

-0.14

arella

-0.13

ylko

-0.13

 Wanna

-0.13

 Avoid

-0.13

éģ¿

-0.13

Pru

-0.13

OT

-0.13

POSITIVE LOGITS

 control

0.52

control

0.46

 Control

0.42

 ownership

0.41

-control

0.40

 CONTROL

0.39

Control

0.37

 controle

0.37

_control

0.36

 kontrol

0.36

Activations Density 0.047%

phrases related to power dynamics and authority within societal and educational contexts

No Comments

No Known Activations