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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 111406
    Prev
    Next
    INDEX
    Explanations

    yearly timeline

    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
    tent
    -0.07
     Blood
    -0.07
    Crypto
    -0.07
    -priced
    -0.07
    olds
    -0.07
    {}]
    -0.06
     credited
    -0.06
    ands
    -0.06
     Surface
    -0.06
     sanit
    -0.06
    POSITIVE LOGITS
    !!
    0.08
     topLeft
    0.07
     OnClickListener
    0.06
    88
    0.06
    现在
    0.06
    ・・
    0.06
    _MON
    0.06
     gerç
    0.06
    ほど
    0.06
    oday
    0.06
    Activations Density 0.010%

    No Known Activations