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. 19-RESID-POST-AA
    6. 57560
    Prev
    Next
    INDEX
    Explanations

    data sets

    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
    Ds
    -0.07
    birthdate
    -0.07
    爵
    -0.07
    Met
    -0.06
    ambre
    -0.06
    λώ
    -0.06
    sts
    -0.06
    Dia
    -0.06
    Zero
    -0.06
    穴
    -0.06
    POSITIVE LOGITS
    业务
    0.07
     propriet
    0.06
     blackmail
    0.06
    献
    0.06
    [frame
    0.06
     jealousy
    0.06
     professors
    0.06
     '['
    0.06
     mercy
    0.06
     adicion
    0.05
    Activations Density 0.024%

    No Known Activations