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. 84035
    Prev
    Next
    INDEX
    Explanations

    Code/math snippets

    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
    Wy
    -0.06
    орая
    -0.06
    ”↵↵
    -0.06
     Rolls
    -0.06
     Any
    -0.06
    %s
    -0.06
    macı
    -0.06
    ันท
    -0.06
     celebration
    -0.06
     Commissioner
    -0.06
    POSITIVE LOGITS
     баг
    0.07
     куль
    0.07
     textView
    0.06
    tright
    0.06
    textView
    0.06
    \models
    0.06
    =%
    0.06
     жін
    0.06
    flix
    0.06
    혁
    0.06
    Activations Density 0.020%

    No Known Activations