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. 44955
    Prev
    Next
    INDEX
    Explanations

    passenger

    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
    叶
    -0.07
    petto
    -0.06
     drills
    -0.06
    gold
    -0.06
     OLD
    -0.06
     certificate
    -0.06
    EW
    -0.06
     book
    -0.06
     프로그램
    -0.06
    Swap
    -0.06
    POSITIVE LOGITS
     passengers
    0.08
    ember
    0.07
     passenger
    0.07
    panied
    0.07
     Passenger
    0.07
    panion
    0.07
     Carson
    0.07
    '=>$_
    0.07
    connected
    0.07
    preg
    0.07
    Activations Density 0.004%

    No Known Activations