INDEX

Explanations

references to military installations and environmental contamination

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

-Token

-0.15

 Synd

-0.15

zt

-0.15

assin

-0.14

ActionCreators

-0.14

vez

-0.13

 Saul

-0.13

Ã²i

-0.13

ominator

-0.13

 resc

-0.13

POSITIVE LOGITS

 base

0.32

 installation

0.31

 Base

0.31

 Installation

0.30

 Camp

0.29

 installations

0.29

 bases

0.26

Installation

0.26

-base

0.25

installation

0.25

Activations Density 0.061%

references to military installations and environmental contamination

No Comments

No Known Activations