© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 89416
    Prev
    Next
    INDEX
    Explanations

    sexual consent and assault

    np_max-act · gemini-2.0-flash

    The neuron activates primarily on terms referring to sexual acts or contexts (e.g. “sexual,” “activity,” “encounter,” etc.).

    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
     arms
    -0.06
    補
    -0.06
     dll
    -0.06
    .math
    -0.06
    EQ
    -0.06
    /dashboard
    -0.06
    ใส
    -0.06
    .sound
    -0.06
     기타
    -0.06
     Reduction
    -0.06
    POSITIVE LOGITS
     Virginia
    0.08
     Wohn
    0.07
    istra
    0.07
     nâng
    0.07
    ederland
    0.07
    venge
    0.07
     gouver
    0.06
     offen
    0.06
     А
    0.06
    vin
    0.06
    Activations Density 0.026%

    No Known Activations