INDEX

Explanations

vulnerable

np_max-act · gemini-2.0-flash

This neuron selectively activates on the root “vulnerab” (i.e. the word “vulnerable” or “vulnerability”).

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

(sc

-0.07

 disco

-0.07

 skiing

-0.06

 Esther

-0.06

 slightest

-0.06

 Stafford

-0.06

 carriage

-0.06

OSX

-0.06

POSITIVE LOGITS

 vulnerable

0.16

 vulnerability

0.14

 vulnerabilities

0.10

 vulner

0.10

 looph

0.08

voucher

0.08

 fragile

0.08

 Vulner

0.08

 uzav

0.08

ování

0.08

Activations Density 0.006%

vulnerable

This neuron selectively activates on the root “vulnerab” (i.e. the word “vulnerable” or “vulnerability”).

No Comments

No Known Activations