INDEX

Explanations

ValueHandling, Decoder

np_max-act · gemini-2.0-flash

The neuron fires on mentions of JSON (de)serialization calls and settings (e.g. Decoder, Encoder, ValueHandling).

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

な

-0.07

 mView

-0.06

 helper

-0.06

.navigate

-0.06

Initialize

-0.06

	append

-0.06

อากาศ

-0.06

 Tarihi

-0.06

_scalar

-0.06

 Australians

-0.06

POSITIVE LOGITS

').'

0.07

doubleValue

0.07

oured

0.06

Kb

0.06

 Soft

0.06

.","

0.06

UV

0.06

ONLY

0.06

ительства

0.06

Activations Density 0.000%

ValueHandling, Decoder

The neuron fires on mentions of JSON (de)serialization calls and settings (e.g. Decoder, Encoder, ValueHandling).

No Comments

No Known Activations

ValueHandling, Decoder

The neuron fires on mentions of JSON (de)serialization calls and settings (e.g. Decoder, Encoder, ValueHandling).

No Comments

No Known Activations