© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 68255
    Prev
    Next
    INDEX
    Explanations

    configuration/code

    np_max-act · gemini-2.0-flash

    This neuron activates on Vue single-file component section tags (e.g. `<template>`, `<script>`, `<style>`).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    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
    olving
    -0.07
    пра
    -0.07
     物
    -0.07
    osp
    -0.06
    ип
    -0.06
     (
    -0.06
    Once
    -0.06
    caffe
    -0.06
    ерк
    -0.06
    BF
    -0.06
    POSITIVE LOGITS
     }}"></
    0.07
    ")))
    0.07
     Mein
    0.06
     bulunmaktadır
    0.06
    acağız
    0.06
    _UnityEngine
    0.06
    _shared
    0.06
     stroll
    0.06
     tsl
    0.06
     SignUp
    0.06
    Activations Density 0.191%

    No Known Activations