INDEX

Explanations

Punctuation

np_max-act · gemini-2.0-flash

This neuron detects the labeled “premise:” marker (i.e. the word “premise” followed by a colon).

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

.real

-0.07

Bí

-0.07

 renders

-0.07

-0.06

 Readers

-0.06

Delete

-0.06

 friend

-0.06

 originates

-0.06

Man

-0.06

 gatherings

-0.06

POSITIVE LOGITS

 political

0.07

 Gi�

0.06

\Framework

0.06

ebb

0.06

imiento

0.06

 بود

0.06

�

0.06

 thầu

0.06

잡

0.06

_Construct

0.06

Activations Density 0.007%

Punctuation

This neuron detects the labeled “premise:” marker (i.e. the word “premise” followed by a colon).

No Comments

No Known Activations