INDEX

Explanations

references to tax-related topics and regulations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

longleftrightarrow

-0.17

ÐłÐĺ

-0.15

rove

-0.15

variants

-0.15

lement

-0.15

ëŀ

-0.15

HIR

-0.15

 taxes

-0.14

hrs

-0.14

ACEMENT

-0.14

POSITIVE LOGITS

onomic

0.23

onomies

0.20

onom

0.20

payer

0.19

ider

0.19

 shelter

0.19

 advant

0.18

 breaks

0.17

 break

0.17

ation

0.17

Activations Density 0.014%

references to tax-related topics and regulations

No Comments

No Known Activations