INDEX

Explanations

Internal thoughts and feelings

np_max-act · gemini-2.0-flash

This neuron never activates—it doesn’t respond to any token patterns.

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

develop

-0.07

وية

-0.07

UNICATION

-0.07

 polarity

-0.06

asm

-0.06

UES

-0.06

+y

-0.06

 سن

-0.06

rending

-0.06

 numbered

-0.06

POSITIVE LOGITS

odář

0.07

 jetzt

0.07

 srov

0.06

 hospodář

0.06

 ліс

0.06

 прекрас

0.06

 DateTimeOffset

0.06

 zengin

0.06

 ekonomik

0.06

GroupId

0.06

Activations Density 0.034%

Internal thoughts and feelings

This neuron never activates—it doesn’t respond to any token patterns.

No Comments

No Known Activations

Internal thoughts and feelings

This neuron never activates—it doesn’t respond to any token patterns.

No Comments

No Known Activations