INDEX

Explanations

cannot/not

np_max-act · gemini-2.0-flash

The neuron activates specifically on the token “cannot,” flagging explicit expressions of inability or negation.

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

Iss

-0.07

 jego

-0.07

Subscriber

-0.06

 баб

-0.06

HX

-0.06

"{

-0.06

PDF

-0.06

ana

-0.06

igli

-0.06

POSITIVE LOGITS

ecessarily

0.07

 مساحت

0.06

数量

0.06

_NOW

0.06

.NaN

0.06

기도

0.06

_enabled

0.06

 BindingFlags

0.06

ічні

0.06

 worldview

0.06

Activations Density 0.001%

cannot/not

The neuron activates specifically on the token “cannot,” flagging explicit expressions of inability or negation.

No Comments

No Known Activations