INDEX

Explanations

creativity

np_max-act · gemini-2.0-flash

The neuron is responsive to verbs that describe steps or methods—i.e. action words in instructional or “how-to” contexts.

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

 Solic

-0.07

 obtains

-0.07

-Free

-0.06

-example

-0.06

cookies

-0.06

_WIDTH

-0.06

TeX

-0.06

 feasibility

-0.06

cut

-0.06

ila

-0.06

POSITIVE LOGITS

 MASS

0.07

 між

0.07

 francais

0.06

 Christine

0.06

 seventy

0.06

Hopefully

0.06

 багать

0.06

isks

0.06

 второй

0.06

myModalLabel

0.06

Activations Density 0.237%

creativity

The neuron is responsive to verbs that describe steps or methods—i.e. action words in instructional or “how-to” contexts.

No Comments

No Known Activations