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. 123524
    Prev
    Next
    INDEX
    Explanations

    3

    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
    .account
    -0.07
    Cart
    -0.07
    Props
    -0.07
    _NAV
    -0.07
    _dir
    -0.07
    -dismiss
    -0.07
    Bin
    -0.07
    captcha
    -0.06
     IH
    -0.06
     jest
    -0.06
    POSITIVE LOGITS
     Magick
    0.07
     surprises
    0.06
    Unavailable
    0.06
     Armour
    0.06
     cook
    0.06
    さら
    0.06
     [+
    0.06
    //↵↵
    0.06
     embraces
    0.05
    .goto
    0.05
    Activations Density 0.009%

    No Known Activations