INDEX

Explanations

experience

np_max-act · gemini-2.0-flash

The neuron activates on mentions of “experience” or “experiences” (and close variants) describing the authors’ clinical or practical findings.

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

.old

-0.07

ीश

-0.06

Functions

-0.06

	audio

-0.06

_up

-0.06

 juego

-0.06

Minus

-0.06

-tools

-0.06

帽

-0.06

 Appointment

-0.06

POSITIVE LOGITS

 meddling

0.07

 ushort

0.06

 использ

0.06

wn

0.06

(nd

0.06

 allowing

0.06

 practices

0.06

@Json

0.06

+"<

0.06

 seznam

0.06

Activations Density 0.014%

experience

The neuron activates on mentions of “experience” or “experiences” (and close variants) describing the authors’ clinical or practical findings.

No Comments

No Known Activations