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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 101475
    Prev
    Next
    INDEX
    Explanations

    Scientific publications with citations

    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
     Solve
    -0.06
     great
    -0.06
    ragment
    -0.06
    .Getenv
    -0.06
    PLL
    -0.06
    _else
    -0.05
    rap
    -0.05
     Nice
    -0.05
     Dit
    -0.05
    üyük
    -0.05
    POSITIVE LOGITS
    Helvetica
    0.07
    -half
    0.07
    odash
    0.07
    /kubernetes
    0.07
    án
    0.06
     projekt
    0.06
    ------------↵
    0.06
    Architecture
    0.06
     LoginActivity
    0.06
     imagin
    0.06
    Activations Density 0.004%

    No Known Activations