INDEX

Explanations

positive experiences

np_max-act · gemini-2.0-flash

This neuron detects words referring to emotional or psychological experiences, especially ones signaling trauma or distress.

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

 killer

-0.07

/";↵↵

-0.07

ریق

-0.06

адки

-0.06

feld

-0.06

flight

-0.06

/";↵

-0.06

 Goldberg

-0.06

 Leah

-0.06

 nigeria

-0.06

POSITIVE LOGITS

ator

0.07

 MediaType

0.06

_IDENT

0.06

 VERY

0.06

.setSize

0.06

duced

0.06

==============↵

0.06

Cal

0.06

ATOR

0.06

 tego

0.06

Activations Density 0.204%

positive experiences

This neuron detects words referring to emotional or psychological experiences, especially ones signaling trauma or distress.

No Comments

No Known Activations