INDEX

Explanations

what

np_max-act · gemini-2.0-flash

The neuron detects tokens in clarification requests—phrases where the assistant asks the user to provide more context or explain what they mean.

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

 Convenient

-0.06

 thủy

-0.06

_user

-0.06

ач

-0.06

“我

-0.06

печ

-0.06

toInt

-0.06

 Celtics

-0.06

_BG

-0.06

.ReadUInt

-0.06

POSITIVE LOGITS

balances

0.07

 nói

0.06

‌پدیا

0.06

elight

0.06

textfield

0.06

CKET

0.06

 fucked

0.06

 اروپا

0.06

actions

0.06

_deck

0.06

Activations Density 0.022%

what

The neuron detects tokens in clarification requests—phrases where the assistant asks the user to provide more context or explain what they mean.

No Comments

No Known Activations

what

The neuron detects tokens in clarification requests—phrases where the assistant asks the user to provide more context or explain what they mean.

No Comments

No Known Activations