INDEX

Explanations

names

np_max-act · gemini-2.0-flash

The neuron strongly responds to character name placeholders (e.g. “NAME_1”) and personal pronouns referring to those characters.

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Standards

-0.07

ає

-0.06

еса

-0.06

 فرو

-0.06

surname

-0.06

	children

-0.06

(column

-0.06

 البحر

-0.06

цион

-0.06

 Islands

-0.06

POSITIVE LOGITS

망

0.06

 Thus

0.06

.randn

0.06

 yıldız

0.06

 isLoading

0.06

 preventative

0.06

.date

0.06

 ming

0.06

 Mayıs

0.06

 cmds

0.06

Activations Density 0.057%

names

The neuron strongly responds to character name placeholders (e.g. “NAME_1”) and personal pronouns referring to those characters.

No Comments

No Known Activations