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. 19-RESID-POST-AA
    6. 57380
    Prev
    Next
    INDEX
    Explanations

    until/till

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     birlik
    -0.07
    ksen
    -0.07
    few
    -0.07
     얼굴
    -0.06
     treason
    -0.06
    ились
    -0.06
    iptables
    -0.06
    мещ
    -0.06
    KHR
    -0.06
     ResourceBundle
    -0.06
    POSITIVE LOGITS
    _continuous
    0.07
     ש
    0.07
    .dom
    0.07
     Sense
    0.07
     lenght
    0.07
    distinct
    0.07
     Boca
    0.06
    Exists
    0.06
    ENSE
    0.06
     Prel
    0.06
    Activations Density 0.024%

    No Known Activations