INDEX

Explanations

sentences expressing personal opinions or states of being

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

 INTERRUPTION

-0.15

ingen

-0.15

rising

-0.14

okino

-0.14

 aston

-0.14

better

-0.14

 DEALINGS

-0.14

olo

-0.14

uiltin

-0.13

obec

-0.13

POSITIVE LOGITS

 sold

0.32

 Sold

0.26

 onboard

0.26

 partial

0.25

sold

0.24

 fans

0.24

 into

0.23

 SOLD

0.23

 Team

0.23

Team

0.21

Activations Density 0.106%

sentences expressing personal opinions or states of being

No Comments

No Known Activations