INDEX

Explanations

programming questions

np_max-act · gemini-2.0-flash

The neuron fires on words used to frame advice or instructions (e.g. should, need, could, you, this).

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

 пон

-0.07

สาร

-0.07

BOVE

-0.07

енные

-0.07

 fois

-0.06

ERR

-0.06

SIL

-0.06

SCALE

-0.06

.pk

-0.06

SYS

-0.06

POSITIVE LOGITS

 resist

0.07

Boot

0.07

 CONST

0.07

 만들

0.07

 مسیر

0.07

/↵↵

0.07

ủi

0.06

应当

0.06

}))↵↵

0.06

Activations Density 0.147%

programming questions

The neuron fires on words used to frame advice or instructions (e.g. should, need, could, you, this).

No Comments

No Known Activations