INDEX

Explanations

Autobots or robots

np_max-act · gemini-2.0-flash

This neuron detects fragments of Transformers faction names (e.g. “Decepticon” and “Autobot”).

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

관련

-0.07

/icon

-0.06

 Incontri

-0.06

 Apollo

-0.06

/ubuntu

-0.06

("");

-0.06

OCUMENT

-0.06

امه

-0.06

-Russian

-0.06

POSITIVE LOGITS

 vér

0.08

 audit

0.07

Tyler

0.07

 socialist

0.06

 représ

0.06

 Clip

0.06

?↵

0.06

 Cong

0.06

cz

0.06

_sig

0.06

Activations Density 0.004%

Autobots or robots

This neuron detects fragments of Transformers faction names (e.g. “Decepticon” and “Autobot”).

No Comments

No Known Activations

Autobots or robots

This neuron detects fragments of Transformers faction names (e.g. “Decepticon” and “Autobot”).

No Comments

No Known Activations