INDEX

Explanations

phrases indicating possession or ownership

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

licity

-0.14

iloc

-0.14

 Repo

-0.14

las

-0.14

roupe

-0.14

REV

-0.14

plorer

-0.14

antan

-0.14

ãĥ³

-0.14

eced

-0.14

POSITIVE LOGITS

 plans

0.17

0.15

abe

0.14

 upcoming

0.14

 forthcoming

0.14

 theory

0.14

vice

0.13

uh

0.13

umann

0.13

amaz

0.13

Activations Density 0.088%

phrases indicating possession or ownership

No Comments

No Known Activations