INDEX

Explanations

ress

np_max-act · gemini-2.0-flash

The neuron is specialized to pick up mentions of “stress” (and its variants like stressed, stress-induced, etc.).

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

 initiation

-0.08

Gram

-0.07

 halt

-0.07

 conjug

-0.07

 upward

-0.07

 naam

-0.07

 banker

-0.07

aub

-0.06

єн

-0.06

 division

-0.06

POSITIVE LOGITS

 stress

0.16

 Stress

0.13

 stresses

0.10

stress

0.09

 stressing

0.08

 stressful

0.08

 distressed

0.08

 stressed

0.08

mass

0.07

PRESS

0.07

Activations Density 0.010%

ress

The neuron is specialized to pick up mentions of “stress” (and its variants like stressed, stress-induced, etc.).

No Comments

No Known Activations