© 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. 7-RESID-POST-AA
    11. 63235
    Prev
    Next
    INDEX
    Explanations

    Medical case studies

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Drama
    -0.07
    權
    -0.07
     Đây
    -0.07
     �
    -0.07
    Ted
    -0.06
     مرک
    -0.06
    fasta
    -0.06
     हट
    -0.06
    DataGridView
    -0.06
    :init
    -0.06
    POSITIVE LOGITS
    Convention
    0.06
    aft
    0.06
    州市
    0.06
    стро
    0.06
     ></
    0.06
     Demir
    0.06
    >Select
    0.06
    SL
    0.06
    jured
    0.06
    izes
    0.06
    Activations Density 0.078%

    No Known Activations