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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 123112
    Prev
    Next
    INDEX
    Explanations

    ,

    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
     Hàng
    -0.06
    Soon
    -0.06
     सफ
    -0.06
    ario
    -0.06
    .Uint
    -0.06
     Gä
    -0.06
     هزینه
    -0.06
    criptive
    -0.06
    ประมาณ
    -0.06
    roring
    -0.05
    POSITIVE LOGITS
    İng
    0.07
    다면
    0.07
     collagen
    0.07
    EDIATEK
    0.07
     thrust
    0.06
    면
    0.06
    %!
    0.06
    Noise
    0.06
     speaking
    0.06
     стол
    0.06
    Activations Density 0.000%

    No Known Activations