INDEX

Explanations

illusion

np_max-act · gemini-2.0-flash

This neuron never activates (i.e. it does not respond to any tokens).

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

	startActivity

-0.07

 Ramsey

-0.06

.Description

-0.06

Gender

-0.06

 предпри

-0.06

.Timestamp

-0.06

pager

-0.06

 Stark

-0.06

 scrutiny

-0.06

 Franco

-0.06

POSITIVE LOGITS

 illusion

0.11

 illusions

0.10

illusion

0.09

YLES

0.08

 elusive

0.08

각

0.08

UL

0.07

ايل

0.07

 UIManager

0.07

ilos

0.07

Activations Density 0.004%

illusion

This neuron never activates (i.e. it does not respond to any tokens).

No Comments

No Known Activations

illusion

This neuron never activates (i.e. it does not respond to any tokens).

No Comments

No Known Activations