© 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. 7-RESID-POST-AA
    11. 7669
    Prev
    Next
    INDEX
    Explanations

    I

    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
    740
    -0.06
    left
    -0.06
    GER
    -0.06
     morality
    -0.06
    ुल
    -0.06
     included
    -0.06
    ToSelector
    -0.06
    lever
    -0.06
    trained
    -0.05
     Δε
    -0.05
    POSITIVE LOGITS
     Rp
    0.07
     Default
    0.06
    」を
    0.06
    ')↵
    0.06
     peak
    0.06
     sponsored
    0.06
    .close
    0.06
     přízn
    0.06
     default
    0.06
    .clear
    0.06
    Activations Density 0.107%

    No Known Activations