INDEX

Explanations

scheduled events

np_max-act · gemini-2.0-flash

This neuron activates on words referring to academic instruction contexts—e.g. “class,” “lesson,” and “lecture.”

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

 Свят

-0.06

어나

-0.06

_planes

-0.06

ldap

-0.06

 unarmed

-0.06

あげ

-0.06

导致

-0.06

corn

-0.06

 Shade

-0.06

 Athletic

-0.06

POSITIVE LOGITS

ANGER

0.07

 слож

0.07

 фай

0.07

北

0.07

uppe

0.07

 kanıt

0.07

;↵↵↵↵

0.07

Canonical

0.07

])↵↵↵

0.06

        
↵
↵

0.06

Activations Density 0.054%

scheduled events

This neuron activates on words referring to academic instruction contexts—e.g. “class,” “lesson,” and “lecture.”

No Comments

No Known Activations