© 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. 11-RESID-POST-AA
    6. 79542
    Prev
    Next
    INDEX
    Explanations

    offset

    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
     Sp
    -0.06
     Meredith
    -0.06
     nova
    -0.06
     aggression
    -0.06
    favorites
    -0.06
    .Marshal
    -0.06
    τογραφ
    -0.06
     gettext
    -0.06
     Craft
    -0.06
    州市
    -0.05
    POSITIVE LOGITS
    Estimated
    0.07
     absence
    0.07
    ними
    0.07
     tome
    0.06
    užel
    0.06
    .GONE
    0.06
    _Close
    0.06
     PhpStorm
    0.06
    Inset
    0.06
     shove
    0.06
    Activations Density 0.021%

    No Known Activations