© 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. 42640
    Prev
    Next
    INDEX
    Explanations

    javascript object methods

    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
     tä
    -0.08
    *scale
    -0.07
    =E
    -0.06
    Callback
    -0.06
     cabin
    -0.06
     Seg
    -0.06
     заг
    -0.06
    makt
    -0.06
     debacle
    -0.06
     Thông
    -0.06
    POSITIVE LOGITS
    roperties
    0.07
     valueForKey
    0.07
    ër
    0.07
                        ↵
    0.06
     FileAccess
    0.06
    ()-
    0.06
    itaire
    0.06
     microbes
    0.06
    ')):↵
    0.06
    окумент
    0.06
    Activations Density 0.003%

    No Known Activations