Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 23-RESID-POST-AA
    6. 103827
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    なが
    -0.07
    terminal
    -0.06
    _ADDR
    -0.06
    ISyntaxException
    -0.06
    Var
    -0.06
    gements
    -0.06
    answers
    -0.06
    图
    -0.06
    jde
    -0.06
     may
    -0.06
    POSITIVE LOGITS
    (te
    0.07
     Usuarios
    0.07
     isNew
    0.06
    _SETUP
    0.06
     squ
    0.06
    ประม
    0.06
     الب
    0.06
    :none
    0.06
     vinc
    0.06
     Consolid
    0.06
    Activations Density 0.060%

    No Known Activations