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

    Neuronpedia

    APICircuit 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. 111039
    Prev
    Next
    INDEX
    Explanations

    URLs and random characters

    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
     soils
    -0.07
     Cellular
    -0.07
     Shapiro
    -0.06
     الوقت
    -0.06
    _key
    -0.06
     tiện
    -0.06
    FilePath
    -0.06
    thalm
    -0.06
     orbit
    -0.06
    ixmap
    -0.06
    POSITIVE LOGITS
    >
    0.06
     Getty
    0.06
    ­ing
    0.06
     iPhone
    0.06
     Lisbon
    0.06
     Xã
    0.06
    getStringExtra
    0.06
    iPhone
    0.06
    $core
    0.06
    scr
    0.06
    Activations Density 0.071%

    No Known Activations