INDEX

Explanations

references to the usage and purpose of personal information in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

æĭ©

-0.15

bject

-0.14

 Interpret

-0.14

hydr

-0.14

è·¡

-0.14

beit

-0.13

 Outside

-0.13

ereco

-0.13

 abroad

-0.13

POSITIVE LOGITS

 internal

0.29

 inside

0.28

inside

0.26

åĨħéĥ¨

0.25

 INTERNAL

0.25

_inside

0.25

internal

0.24

Inside

0.24

 Inside

0.23

 Internal

0.22

Activations Density 0.005%

references to the usage and purpose of personal information in various contexts

No Comments

No Known Activations