© 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. 54395
    Prev
    Next
    INDEX
    Explanations

    creating

    np_max-act · gemini-2.0-flash

    The neuron activates on passive‐voice verb phrases (e.g., “has been proposed,” “are being made,” “is formed,” “is conducted”).

    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
     مسلمان
    -0.08
    仰
    -0.07
    het
    -0.07
    วย
    -0.07
    _iterations
    -0.06
    اته
    -0.06
     fullest
    -0.06
    ense
    -0.06
    igne
    -0.06
    >`↵
    -0.06
    POSITIVE LOGITS
     registering
    0.06
     dern
    0.06
    -plus
    0.06
    .Country
    0.06
    _NAMES
    0.06
    -register
    0.06
     yüzde
    0.06
     oluştur
    0.06
    _perm
    0.06
    とな
    0.06
    Activations Density 0.145%

    No Known Activations