INDEX

Explanations

phrases that express purpose or intent

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

ope

-0.16

ORMAT

-0.16

isers

-0.15

opis

-0.15

é¤

-0.15

erten

-0.15

dad

-0.15

icies

-0.14

\CMS

-0.14

itter

-0.14

POSITIVE LOGITS

ges

0.18

 Dirty

0.17

 purposes

0.16

amt

0.16

ster

0.15

ay

0.15

amu

0.15

sko

0.15

chter

0.15

ged

0.15

Activations Density 0.250%

phrases that express purpose or intent

No Comments

No Known Activations