Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 110639
    Prev
    Next
    INDEX
    Explanations

    sex

    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
    vides
    -0.06
     consulting
    -0.06
     planes
    -0.06
     copyrights
    -0.06
    .city
    -0.06
     taxi
    -0.06
     report
    -0.06
    .Repository
    -0.06
    _printer
    -0.06
     plane
    -0.06
    POSITIVE LOGITS
    宣
    0.08
     CoreData
    0.07
    agenda
    0.07
    walking
    0.07
    venida
    0.07
    /proto
    0.07
    conexion
    0.07
    ACCEPT
    0.06
    ź
    0.06
    џџџџџџџџџџџџџџџџџџџџџџџџџџџџџџџџ
    0.06
    Activations Density 0.028%

    No Known Activations