© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 7-RESID-POST-AA
    6. 94509
    Prev
    Next
    INDEX
    Explanations

    shown

    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
    @nate
    -0.07
    -write
    -0.06
    اسية
    -0.06
    мос
    -0.06
    jvu
    -0.06
     Facilities
    -0.06
    asc
    -0.06
     explos
    -0.06
     fracking
    -0.06
     OP
    -0.06
    POSITIVE LOGITS
     trademarks
    0.06
    .getPath
    0.06
    Inter
    0.06
    '].'
    0.06
     بيانات
    0.06
     Inter
    0.06
    .LookAndFeel
    0.06
     Provid
    0.06
    _WIDGET
    0.06
     Baltimore
    0.06
    Activations Density 0.029%

    No Known Activations