© 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. 3-RESID-POST-AA
    11. 121282
    Prev
    Next
    INDEX
    Explanations

    Hugh

    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_3/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     occurrence
    -0.07
    ���
    -0.07
     Components
    -0.07
     product
    -0.06
    making
    -0.06
     disrupting
    -0.06
    around
    -0.06
     factors
    -0.06
     cursed
    -0.06
     ات
    -0.06
    POSITIVE LOGITS
     Hugh
    0.36
    Hugh
    0.28
     Giles
    0.14
     Hughes
    0.12
     Dirk
    0.10
    择
    0.07
    DBObject
    0.07
    =no
    0.06
    UGH
    0.06
     CHtml
    0.06
    Activations Density 0.001%

    No Known Activations