INDEX

Explanations

comma

np_max-act · gemini-2.0-flash

The neuron fires on the occurrence of the word “modify,” as found in license‐style permission statements.

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

ğı

-0.07

osto

-0.07

 Damen

-0.07

 NEWS

-0.07

/type

-0.06

 testName

-0.06

导

-0.06

 Shot

-0.06

体

-0.06

Il

-0.06

POSITIVE LOGITS

_episode

0.07

 कव

0.07

KHR

0.06

บ

0.06

reative

0.06

inet

0.06

":[-

0.06

 tieten

0.06

-earth

0.06

 กรก

0.06

Activations Density 0.001%

comma

The neuron fires on the occurrence of the word “modify,” as found in license‐style permission statements.

No Comments

No Known Activations

comma

The neuron fires on the occurrence of the word “modify,” as found in license‐style permission statements.

No Comments

No Known Activations