INDEX

Explanations

anecdotes

np_max-act · gemini-2.0-flash

This neuron detects first‐person, self‐referential language (e.g. “I,” “my,” “once,” “years ago”) indicating personal anecdotes or narration.

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

 VMware

-0.08

btc

-0.07

 viewPager

-0.06

 VIII

-0.06

.MSG

-0.06

Wig

-0.06

 PERSON

-0.06

 Максим

-0.06

엄

-0.06

/post

-0.06

POSITIVE LOGITS

oubles

0.06

ipl

0.06

everything

0.06

_leaf

0.06

Doing

0.06

......↵↵

0.06

'être

0.06

Secondary

0.06

Dt

0.06

	date

0.06

Activations Density 0.049%

anecdotes

This neuron detects first‐person, self‐referential language (e.g. “I,” “my,” “once,” “years ago”) indicating personal anecdotes or narration.

No Comments

No Known Activations