© 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 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. 27-RESID-POST-AA
    11. 9065
    Prev
    Next
    INDEX
    Explanations

    ground

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_27/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     echo
    -0.07
     Elizabeth
    -0.07
    ella
    -0.07
    Elizabeth
    -0.06
    _epsilon
    -0.06
     fick
    -0.06
     didSelect
    -0.06
     dile
    -0.06
     aficion
    -0.06
     Nike
    -0.06
    POSITIVE LOGITS
     ground
    0.11
    Ground
    0.09
     Ground
    0.08
    grounds
    0.08
     pornôs
    0.08
     ΑΝ
    0.07
    -ground
    0.07
     Guidance
    0.07
    Thrown
    0.07
    _ground
    0.07
    Activations Density 0.015%

    No Known Activations