INDEX

Explanations

terms related to hypnosis and affirmative techniques

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

McN

-0.15

YM

-0.15

olic

-0.15

uppen

-0.15

éĤ

-0.15

 surf

-0.14

 Syndrome

-0.14

ä¼Ŀ

-0.14

 Randall

-0.14

 Contrib

-0.14

POSITIVE LOGITS

hyp

0.21

 hypnot

0.19

 Ð²Ð½Ñĥ

0.19

åĤ¬

0.18

 programming

0.18

 Deep

0.17

 trance

0.17

hyp

0.17

programming

0.17

 Programming

0.16

Activations Density 0.040%

terms related to hypnosis and affirmative techniques

No Comments

No Known Activations