INDEX

Explanations

punctuation

np_max-act · gemini-2.0-flash

The neuron flags mentions of personal trauma or adversity, especially injuries, medical crises, and emotional suffering.

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

 EXPECT

-0.06

 varying

-0.06

mask

-0.06

id

-0.06

 Ident

-0.06

_FIELDS

-0.06

 handlers

-0.06

_SHORT

-0.06

、「

-0.06

 seins

-0.06

POSITIVE LOGITS

 Finland

0.07

agher

0.07

θ

0.06

ormsg

0.06

_each

0.06

ουσ

0.06

setStatus

0.06

 radius

0.06

-stack

0.06

 slang

0.06

Activations Density 0.043%

punctuation

The neuron flags mentions of personal trauma or adversity, especially injuries, medical crises, and emotional suffering.

No Comments

No Known Activations