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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 104855
    Prev
    Next
    INDEX
    Explanations

    Hick

    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
     vyrob
    -0.07
     gev
    -0.06
     Io
    -0.06
    	method
    -0.06
    ...\
    -0.06
     chest
    -0.06
     سرم
    -0.06
     Alban
    -0.06
     psychiat
    -0.06
     Frog
    -0.06
    POSITIVE LOGITS
     Devils
    0.07
     Gtk
    0.07
     setActive
    0.07
    аки
    0.07
    ями
    0.07
    ح
    0.07
    EXEC
    0.07
    _MINOR
    0.07
    MemoryWarning
    0.06
    ?)
    0.06
    Activations Density 0.001%

    No Known Activations