© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 54256
    Prev
    Next
    INDEX
    Explanations

    looking

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     设置
    -0.07
    妙
    -0.07
     Adolf
    -0.07
    地区
    -0.07
     extravagant
    -0.07
    /y
    -0.07
    fwrite
    -0.06
    imizer
    -0.06
    лом
    -0.06
     newcom
    -0.06
    POSITIVE LOGITS
     commune
    0.07
     muse
    0.06
     inventory
    0.06
     birthdays
    0.06
    unft
    0.06
     owner
    0.06
     undercut
    0.06
     Womens
    0.06
     recruiting
    0.05
    (userName
    0.05
    Activations Density 0.016%

    No Known Activations