INDEX

Explanations

he

np_max-act · gemini-2.0-flash

The neuron is specialized in picking out the special metadata/header markers (e.g. the `<|start_header_id|>`, `<|end_header_id|>`, `<|begin_of_text|>`, `<|eot_id|>` tokens) rather than ordinary words.

oai_token-act-pair · o4-mini Triggered by @xinyanhu8

New Auto-Interp

Configuration

andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.11.hook_resid_post

Architecture

standard

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Basics

-0.07

Uploaded

-0.06

 stereotypes

-0.06

しました

-0.06

_payments

-0.06

 القانون

-0.06

 NASCAR

-0.06

 Manor

-0.06

 renown

-0.06

 landscaping

-0.06

POSITIVE LOGITS

PET

0.07

 checking

0.06

*.

0.06

_CO

0.06

 influ

0.06

می

0.06

-che

0.06

 trolling

0.06

UNCH

0.06

 Checking

0.06

Activations Density 0.034%

he

The neuron is specialized in picking out the special metadata/header markers (e.g. the `<|start_header_id|>`, `<|end_header_id|>`, `<|begin_of_text|>`, `<|eot_id|>` tokens) rather than ordinary words.

No Comments

No Known Activations