© 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
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 124551
    Prev
    Next
    INDEX
    Explanations

    human extinction

    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
    �
    -0.06
     这
    -0.06
    ех
    -0.06
    _af
    -0.06
    แนะ
    -0.06
    ворення
    -0.06
    ация
    -0.06
    부분
    -0.06
    _TESTS
    -0.06
    مین
    -0.06
    POSITIVE LOGITS
     witches
    0.06
    .POST
    0.06
     folders
    0.06
    agua
    0.06
    $table
    0.06
     Cot
    0.06
    opause
    0.06
     tim
    0.06
     nisi
    0.06
     {%
    0.06
    Activations Density 0.025%

    No Known Activations