INDEX

Explanations

mutations

np_max-act · gemini-2.0-flash

The neuron responds to mentions of gene mutations and related genetic alteration terms.

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

LEVEL

-0.07

兄弟

-0.07

 پس

-0.07

HSV

-0.07

 regained

-0.07

рахов

-0.06

	Context

-0.06

７

-0.06

Sector

-0.06

сол

-0.06

POSITIVE LOGITS

 takip

0.06

lyn

0.06

usunda

0.06

 sahip

0.06

dba

0.06

 landed

0.06

�

0.06

bre

0.06

ician

0.06

 winning

0.06

Activations Density 0.009%

mutations

The neuron responds to mentions of gene mutations and related genetic alteration terms.

No Comments

No Known Activations