© 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. 18446
    Prev
    Next
    INDEX
    Explanations

    have

    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
     Rosen
    -0.09
    000
    -0.07
    _pix
    -0.07
    Bubble
    -0.07
     Mas
    -0.06
    Stick
    -0.06
    emd
    -0.06
    Mus
    -0.06
    ии
    -0.06
    Therefore
    -0.06
    POSITIVE LOGITS
     отверсти
    0.07
     involves
    0.06
     rez
    0.06
    .GetDirectoryName
    0.06
    镇
    0.06
    quential
    0.06
     quota
    0.06
     उपलब
    0.06
     convert
    0.06
    �
    0.06
    Activations Density 0.013%

    No Known Activations