INDEX

Explanations

period character

np_max-act · gemini-2.0-flash

This neuron detects floating-point numbers (decimal values) typically appearing in reference or citation metadata.

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

ций

-0.07

_plugins

-0.07

 tisíc

-0.06

CTIONS

-0.06

 Partition

-0.06

ické

-0.06

-char

-0.06

충

-0.06

	selected

-0.06

_bbox

-0.06

POSITIVE LOGITS

 zahrani

0.07

-between

0.06

実

0.06

öff

0.06

 Díky

0.06

 порів

0.06

(et

0.06

 POST

0.06

 ان

0.05

INSERT

0.05

Activations Density 0.009%

period character

This neuron detects floating-point numbers (decimal values) typically appearing in reference or citation metadata.

No Comments

No Known Activations

period character

This neuron detects floating-point numbers (decimal values) typically appearing in reference or citation metadata.

No Comments

No Known Activations