Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 73071
    Prev
    Next
    INDEX
    Explanations

    location names

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IPLE
    -0.07
    _door
    -0.07
     airstrikes
    -0.06
    dden
    -0.06
     dilemma
    -0.06
    Process
    -0.06
    LOTS
    -0.06
    ydı
    -0.06
     vert
    -0.06
     放
    -0.06
    POSITIVE LOGITS
    erli
    0.07
     indie
    0.06
    เม
    0.06
    training
    0.06
    RIA
    0.06
    ें
    0.06
    [contains
    0.06
     그녀
    0.06
    ovol
    0.06
     ere
    0.06
    Activations Density 0.012%

    No Known Activations