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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 39145
    Prev
    Next
    INDEX
    Explanations

    Homes and personal use

    np_max-act · gemini-2.0-flash

    The neuron activates on words that name or describe usage contexts or audience sectors (e.g. home/residential, commercial/business, offices, industries, etc.).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    identify mentions of home or residential contexts (including small/home-office usage).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    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
    .instant
    -0.07
     Metrics
    -0.07
     DOE
    -0.07
     Debug
    -0.06
     Appet
    -0.06
     citation
    -0.06
    323
    -0.06
     shortages
    -0.06
    160
    -0.06
    ورت
    -0.06
    POSITIVE LOGITS
    '],$_
    0.06
    @Test
    0.06
     Conor
    0.06
    ประก
    0.06
     JComboBox
    0.06
     tuyệt
    0.06
    Mitch
    0.06
     possível
    0.06
     escal
    0.06
    нова
    0.06
    Activations Density 0.343%

    No Known Activations