INDEX

Explanations

code

np_max-act · gemini-2.0-flash

This neuron detects code‐comment “TODO” or refactoring markers—especially the word “Rename” in comments.

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

acro

-0.07

 pediatric

-0.06

others

-0.06

üns

-0.06

Picture

-0.06

 crossorigin

-0.06

atum

-0.06

vell

-0.06

ْع

-0.06

ibold

-0.06

POSITIVE LOGITS

0.07

 harmonic

0.07

Ich

0.06

NotAllowed

0.06

 terminating

0.06

 cellForRowAt

0.06

 town

0.06

Instruction

0.06

lbrace

0.06

Activations Density 0.000%

code

This neuron detects code‐comment “TODO” or refactoring markers—especially the word “Rename” in comments.

No Comments

No Known Activations