INDEX

Explanations

terms related to revealing, uncovering, or exposing information and truths

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

ÑĢÐ°Ð¿

-0.17

 ná»ķi

-0.15

ë³

-0.14

 Ð¿ÑĢÐ¾Ð¿Ð¾Ð·Ð¸

-0.14

 ë§ĲìĿ´

-0.14

 VerfÃ¼g

-0.14

gere

-0.14

 kiá»ĩn

-0.13

ÎŃÏģÎ³

-0.13

Privacy

-0.13

POSITIVE LOGITS

 secrets

0.29

 hidden

0.29

 revealing

0.25

 truth

0.25

 truths

0.24

 reveal

0.24

 revealed

0.23

 underlying

0.23

 Truth

0.22

 Secrets

0.22

Activations Density 0.090%

terms related to revealing, uncovering, or exposing information and truths

No Comments

No Known Activations