INDEX

Explanations

See

np_max-act · gemini-2.0-flash

sections of code that include licensing and copyright information.

oai_token-act-pair · gpt-4o-mini Triggered by @xinyanhu8

This neuron activates on comment lines pointing to licensing information (e.g. “See the LICENSE file” references).

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

 sweep

-0.06

Ve

-0.06

 Calculates

-0.06

�

-0.06

meteor

-0.06

 حف

-0.05

Fs

-0.05

 felony

-0.05

 ورود

-0.05

FA

-0.05

POSITIVE LOGITS

 tech

0.08

 definitions

0.07

 Description

0.07

京

0.07

 corporate

0.07

ecd

0.07

 위치

0.07

tz

0.07

 Association

0.07

 selects

0.07

Activations Density 0.004%

See

sections of code that include licensing and copyright information.

This neuron activates on comment lines pointing to licensing information (e.g. “See the LICENSE file” references).

No Comments

No Known Activations