INDEX

Explanations

mathematical expressions

np_max-act · gemini-2.0-flash

This neuron remains inactive on all shown inputs, so it does not detect any specific pattern in these excerpts.

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

LX

-0.07

 Faster

-0.06

 duas

-0.06

 Username

-0.06

 Exclusive

-0.06

 zwei

-0.06

 akşam

-0.06

/tools

-0.06

 founded

-0.06

POSITIVE LOGITS

 blink

0.07

sok

0.06

fel

0.06

ійно

0.06

lul

0.06

εται

0.06

Bracket

0.06

friend

0.06

�

0.06

textBox

0.06

Activations Density 0.016%

mathematical expressions

This neuron remains inactive on all shown inputs, so it does not detect any specific pattern in these excerpts.

No Comments

No Known Activations