INDEX

Explanations

is

np_max-act · gemini-2.0-flash

The neuron fires on little parenthetical clarification cues—phrases like “that is,” “of course,” “i.e.,” etc., used to introduce an explanatory aside.

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

ف

-0.06

 psychiat

-0.06

(""),

-0.06

createUrl

-0.06

Codes

-0.06

 Missouri

-0.06

sns

-0.06

$__

-0.06

 splitting

-0.06

 مما

-0.06

POSITIVE LOGITS

 เร

0.07

어요

0.07

려요

0.07

 Каз

0.07

였다

0.06

 داریم

0.06

しま

0.06

ประกอบ

0.06

Plot

0.06

 громадян

0.06

Activations Density 0.017%

is

The neuron fires on little parenthetical clarification cues—phrases like “that is,” “of course,” “i.e.,” etc., used to introduce an explanatory aside.

No Comments

No Known Activations