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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 99512
    Prev
    Next
    INDEX
    Explanations

    family history

    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
     elite
    -0.07
    mel
    -0.07
    기가
    -0.07
     };↵↵↵
    -0.06
     Fon
    -0.06
    reeze
    -0.06
    riting
    -0.06
     Pes
    -0.06
    892
    -0.06
     gw
    -0.06
    POSITIVE LOGITS
     SCRIPT
    0.06
    _inode
    0.06
     अप
    0.06
     Dickens
    0.06
    .translatesAutoresizingMaskIntoConstraints
    0.06
     жив
    0.06
    (mapStateToProps
    0.06
     praž
    0.06
    _ADMIN
    0.06
    REFER
    0.06
    Activations Density 0.058%

    No Known Activations