INDEX

Explanations

references to specific products and their attributes related to health and construction

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

attery

-0.17

åŀĤ

-0.17

allah

-0.15

ASSES

-0.15

PCODE

-0.15

ochen

-0.15

 oppos

-0.14

keh

-0.14

gregator

-0.14

ê°¤

-0.14

POSITIVE LOGITS

Lok

0.25

pak

0.24

lok

0.23

-lite

0.22

Guard

0.22

Pak

0.22

 Plus

0.22

Plus

0.21

guard

0.21

Lite

0.20

Activations Density 0.285%

references to specific products and their attributes related to health and construction

No Comments

No Known Activations