INDEX

Explanations

take

np_max-act · gemini-2.0-flash

The neuron activates on occurrences of the phrasal verb “take on” (as in “take on anything,” “take on the challenge”).

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

 Nights

-0.07

_least

-0.07

 renew

-0.06

 Resources

-0.06

ця

-0.06

Friday

-0.06

 وجود

-0.06

 overnight

-0.06

 Swords

-0.06

-errors

-0.06

POSITIVE LOGITS

หมาย

0.08

 proactive

0.06

ifter

0.06

BIT

0.06

�

0.06

.epsilon

0.06

.sum

0.06

 Конститу

0.06

 layoffs

0.06

 geri

0.06

Activations Density 0.014%

take

The neuron activates on occurrences of the phrasal verb “take on” (as in “take on anything,” “take on the challenge”).

No Comments

No Known Activations

take

The neuron activates on occurrences of the phrasal verb “take on” (as in “take on anything,” “take on the challenge”).

No Comments

No Known Activations