INDEX

Explanations

clinic

np_max-act · gemini-2.0-flash

This neuron selectively activates on mentions of clinical or care settings (e.g., clinics, outpatient departments, treatment centers).

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

OBJECT

-0.07

 disgust

-0.06

Kut

-0.06

 Unary

-0.06

.OR

-0.06

 Mozart

-0.06

 Chun

-0.06

MED

-0.06

ayın

-0.06

 stoi

-0.06

POSITIVE LOGITS

Nil

0.06

ibern

0.06

 pictured

0.06

.ec

0.06

 superf

0.06

iflower

0.06

     ↵↵

0.05

.sp

0.05

ern

0.05

 digitally

0.05

Activations Density 0.020%

clinic

This neuron selectively activates on mentions of clinical or care settings (e.g., clinics, outpatient departments, treatment centers).

No Comments

No Known Activations

clinic

This neuron selectively activates on mentions of clinical or care settings (e.g., clinics, outpatient departments, treatment centers).

No Comments

No Known Activations