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. 15-RESID-POST-AA
    6. 868
    Prev
    Next
    INDEX
    Explanations

    copyright

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     jugg
    -0.07
    χο
    -0.06
     frække
    -0.06
     작품
    -0.06
    Fs
    -0.06
     wl
    -0.06
     chaired
    -0.06
    orer
    -0.06
    imb
    -0.06
     Logger
    -0.06
    POSITIVE LOGITS
    datepicker
    0.07
    BOOT
    0.06
     **↵
    0.06
    clare
    0.06
     ----------------
    0.06
     plumbing
    0.06
     ethics
    0.06
    564
    0.06
    accounts
    0.06
    clar
    0.06
    Activations Density 0.001%

    No Known Activations