© 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. 11-RESID-POST-AA
    6. 65685
    Prev
    Next
    INDEX
    Explanations

    descriptions

    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
    kud
    -0.06
     několik
    -0.06
    tmp
    -0.06
    �
    -0.06
     crc
    -0.06
    ‌شن
    -0.06
     ob
    -0.06
    DEC
    -0.06
    endsWith
    -0.06
    getError
    -0.05
    POSITIVE LOGITS
    .USER
    0.07
     //////////////////////////////////////////////////////////////////////////
    0.07
    {*
    0.06
    ong
    0.06
    .edit
    0.06
     mash
    0.06
    ONG
    0.06
     force
    0.06
    .Java
    0.06
    _IS
    0.06
    Activations Density 0.210%

    No Known Activations