INDEX

Explanations

references to tax-related deductions and expenses

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

éĢĶ

-0.16

ople

-0.16

appa

-0.15

avana

-0.15

 Leisure

-0.15

sup

-0.14

LOUR

-0.14

åº

-0.14

ann

-0.14

 Regents

-0.14

POSITIVE LOGITS

ATO

0.18

ardy

0.16

expenses

0.15

 qualifying

0.15

á»ĳn

0.15

ymes

0.15

chte

0.14

ä»»

0.14

steder

0.14

 expenses

0.14

Activations Density 0.022%

references to tax-related deductions and expenses

No Comments

No Known Activations