© 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. 15-RESID-POST-AA
    6. 42264
    Prev
    Next
    INDEX
    Explanations

    sex and consent

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tre
    -0.07
    ]);↵
    -0.07
     eu
    -0.07
    ิค
    -0.07
    ACS
    -0.06
    ياه
    -0.06
    PHA
    -0.06
     Cor
    -0.06
    fixtures
    -0.06
     мож
    -0.06
    POSITIVE LOGITS
    cribed
    0.07
    ,double
    0.07
     ongoing
    0.06
    国際
    0.06
     обол
    0.06
     раствор
    0.06
    .kind
    0.06
     fallout
    0.06
    ”的
    0.06
    housing
    0.06
    Activations Density 0.054%

    No Known Activations