INDEX

Explanations

terms related to taxation and tax policies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

iae

-0.16

Ã¼ven

-0.15

-pill

-0.15

agr

-0.15

ecer

-0.15

vt

-0.14

±

-0.14

atter

-0.14

 Pill

-0.14

velt

-0.14

POSITIVE LOGITS

onomies

0.20

onomic

0.18

imeter

0.18

onom

0.18

åĭĻ

0.16

imeters

0.16

payer

0.16

arro

0.15

 Ð¿Ð¾Ð²

0.15

onomy

0.15

Activations Density 0.024%

terms related to taxation and tax policies

No Comments

No Known Activations