INDEX

Explanations

Method

np_max-act · gemini-2.0-flash

The neuron activates on lines from a stack trace, i.e. the method-invocation entries in exception logs.

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

 attracted

-0.07

šetření

-0.07

rz

-0.06

edio

-0.06

Bulk

-0.06

 turbines

-0.06

 WindowManager

-0.06

 gắng

-0.06

_configure

-0.06

 injection

-0.06

POSITIVE LOGITS

-through

0.07

 pitfalls

0.07

 Norwegian

0.06

EL

0.06

-moving

0.06

šli

0.06

	move

0.06

 peripherals

0.06

Esc

0.06

Chooser

0.06

Activations Density 0.000%

Method

The neuron activates on lines from a stack trace, i.e. the method-invocation entries in exception logs.

No Comments

No Known Activations

Method

The neuron activates on lines from a stack trace, i.e. the method-invocation entries in exception logs.

No Comments

No Known Activations