INDEX

Explanations

studies

np_max-act · gemini-2.0-flash

This neuron fires on words in scientific conclusions or discussion that signal caution, uncertainty, or qualification (e.g. caution, interpretation, biased, may) in presenting or interpreting results.

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

esson

-0.07

 очист

-0.07

 commonplace

-0.06

.Current

-0.06

itative

-0.06

 externally

-0.06

 infinitely

-0.06

 trigger

-0.06

Gan

-0.06

 inferior

-0.06

POSITIVE LOGITS

 Yorkshire

0.07

 itemprop

0.06

itage

0.06

criteria

0.06

	operator

0.06

.segments

0.06

_parse

0.06

 Indies

0.06

tokenId

0.06

 Lana

0.06

Activations Density 0.085%

studies

This neuron fires on words in scientific conclusions or discussion that signal caution, uncertainty, or qualification (e.g. caution, interpretation, biased, may) in presenting or interpreting results.

No Comments

No Known Activations

studies

This neuron fires on words in scientific conclusions or discussion that signal caution, uncertainty, or qualification (e.g. caution, interpretation, biased, may) in presenting or interpreting results.

No Comments

No Known Activations