INDEX

Explanations

sl

np_max-act · gemini-2.0-flash

This neuron never activates on any tokens, so it does not detect any specific feature.

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

Ket

-0.07

}}">{{$

-0.07

iliki

-0.06

APolynomial

-0.06

__))

-0.06

 inet

-0.06

 хозя

-0.06

(urls

-0.06

 věn

-0.06

 -*-↵↵

-0.06

POSITIVE LOGITS

音樂

0.07

scores

0.07

 clerk

0.07

 ascertain

0.07

 adjust

0.07

mx

0.06

學

0.06

 according

0.06

.tech

0.06

EndPoint

0.06

Activations Density 0.001%

sl

This neuron never activates on any tokens, so it does not detect any specific feature.

No Comments

No Known Activations

sl

This neuron never activates on any tokens, so it does not detect any specific feature.

No Comments

No Known Activations