© 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. 23-RESID-POST-AA
    11. 63539
    Prev
    Next
    INDEX
    Explanations

    you

    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_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -links
    -0.07
    -------------
    -0.07
    ---------↵↵
    -0.06
    ario
    -0.06
    INE
    -0.06
    anas
    -0.06
     proofs
    -0.06
    ographers
    -0.06
    dv
    -0.06
    Equal
    -0.06
    POSITIVE LOGITS
     відбува
    0.07
    �
    0.06
     Yayın
    0.06
    _UNDER
    0.06
     ΔΗΜ
    0.06
     Γεω
    0.06
     Sioux
    0.06
    fern
    0.06
     uplifting
    0.06
     düşük
    0.06
    Activations Density 0.011%

    No Known Activations