© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 52658
    Prev
    Next
    INDEX
    Explanations

    hacking/security

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ScrollIndicator
    -0.07
    ividual
    -0.07
    ารถ
    -0.06
     Illuminate
    -0.06
    Practice
    -0.06
    indh
    -0.06
     دهید
    -0.06
    ्ध
    -0.06
    usters
    -0.06
    目
    -0.06
    POSITIVE LOGITS
     Arms
    0.06
    autoload
    0.06
    Configure
    0.06
     Collabor
    0.06
     coords
    0.06
    %',
    0.06
     Aynı
    0.06
    _views
    0.06
    >V
    0.06
    승
    0.06
    Activations Density 0.052%

    No Known Activations