© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 32401
    Prev
    Next
    INDEX
    Explanations

    ydro

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -than
    -0.06
     InvalidArgumentException
    -0.06
    .Getter
    -0.06
     iPod
    -0.06
    ToLocal
    -0.06
    Fuck
    -0.06
     Naming
    -0.06
     runaway
    -0.06
     переп
    -0.06
    ์โ
    -0.06
    POSITIVE LOGITS
    ありが
    0.07
    ENSION
    0.07
    paces
    0.07
    anteed
    0.07
     Gonzalez
    0.06
    าท
    0.06
    ález
    0.06
    uates
    0.06
     район
    0.06
    IMATION
    0.06
    Activations Density 0.008%

    No Known Activations