© 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. 42295
    Prev
    Next
    INDEX
    Explanations

    Chemical elements/formulas

    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
     JT
    -0.07
     dedication
    -0.07
    ツ
    -0.06
    pieces
    -0.06
    .Topic
    -0.06
    BX
    -0.06
    様
    -0.06
     phones
    -0.06
     UPLOAD
    -0.06
    .Tools
    -0.06
    POSITIVE LOGITS
     movimiento
    0.07
     velocidad
    0.07
     grad
    0.06
    _cuda
    0.06
     조선
    0.06
     發
    0.06
     koup
    0.06
    isateur
    0.06
     Lebanese
    0.06
    uální
    0.06
    Activations Density 0.152%

    No Known Activations