INDEX

Explanations

Approvals and reviews

np_max-act · gemini-2.0-flash

The neuron specializes in spotting words that refer to formal procedures or regulatory processes (e.g. approval, exception, decision, standards, review).

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

 Wang

-0.06

division

-0.06

озможно

-0.06

 BELOW

-0.06

 cottage

-0.06

眉

-0.06

	container

-0.06

.fac

-0.06

参数

-0.06

 setup

-0.06

POSITIVE LOGITS

assist

0.06

И

0.06

หลวง

0.06

pling

0.06

 tarihi

0.06

 nuanced

0.06

>n

0.06

lexical

0.06

 reasoned

0.06

gh

0.06

Activations Density 0.028%

Approvals and reviews

The neuron specializes in spotting words that refer to formal procedures or regulatory processes (e.g. approval, exception, decision, standards, review).

No Comments

No Known Activations