© 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. 3-RESID-POST-AA
    6. 123578
    Prev
    Next
    INDEX
    Explanations

    3

    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
    2
    -0.08
    StepThrough
    -0.07
    GHz
    -0.06
     lig
    -0.06
    答
    -0.06
    لو
    -0.06
     помог
    -0.06
    وه
    -0.06
    1
    -0.06
    inicio
    -0.06
    POSITIVE LOGITS
    roken
    0.06
    _live
    0.06
    .Light
    0.06
     "')
    0.06
    expanded
    0.06
     //</
    0.06
     relationship
    0.06
    !.↵↵
    0.06
    _non
    0.06
    bidden
    0.06
    Activations Density 0.071%

    No Known Activations