INDEX

Explanations

code snippets

np_max-act · gemini-2.0-flash

The neuron is looking for numeric literal tokens (i.e. standalone numbers) in the text.

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 geç

-0.07

 ندار

-0.07

 Router

-0.07

-0.06

_arr

-0.06

act

-0.06

	null

-0.06

[this

-0.06

 secure

-0.06

 Island

-0.06

POSITIVE LOGITS

 nghiên

0.06

้าม

0.06

ْه

0.06

_third

0.06

\Module

0.06

%%%%%%%%%%%%%%%%

0.06

.IsEmpty

0.06

 Bài

0.06

ApiKey

0.06

/>.↵

0.06

Activations Density 0.016%

code snippets

The neuron is looking for numeric literal tokens (i.e. standalone numbers) in the text.

No Comments

No Known Activations