© 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. 68174
    Prev
    Next
    INDEX
    Explanations

    drug administration

    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
    sts
    -0.07
    五月
    -0.06
    ileceği
    -0.06
    ,pos
    -0.06
    ooting
    -0.06
     relief
    -0.06
    ledo
    -0.06
     wid
    -0.06
    Wiki
    -0.05
     později
    -0.05
    POSITIVE LOGITS
    ting
    0.06
    ometer
    0.06
    	stop
    0.06
    Elite
    0.06
     crave
    0.06
    주세요
    0.06
     quot
    0.06
    bung
    0.06
    ticket
    0.06
    Aaron
    0.06
    Activations Density 0.028%

    No Known Activations