© 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. 57622
    Prev
    Next
    INDEX
    Explanations

    family members

    np_max-act · gemini-2.0-flash

    The neuron fires on words naming or referring to study participant groups or roles (e.g. recipients, parents, mothers, children, adolescents, women).

    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
    sem
    -0.07
     pois
    -0.06
     id
    -0.06
     sleep
    -0.06
     borrowers
    -0.06
     Crow
    -0.06
     VOL
    -0.06
     toilets
    -0.06
    Symbols
    -0.06
    _shuffle
    -0.06
    POSITIVE LOGITS
    .Merge
    0.07
    最後
    0.07
    /upload
    0.07
    LTRB
    0.06
    ?action
    0.06
    adresse
    0.06
    點
    0.06
     itinerary
    0.06
     dejtings
    0.06
     آسی
    0.06
    Activations Density 0.030%

    No Known Activations