© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 84740
    Prev
    Next
    INDEX
    Explanations

    mathematics

    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
     Benefits
    -0.08
    .Import
    -0.07
    report
    -0.07
    	left
    -0.07
    机
    -0.06
    (Parse
    -0.06
     fold
    -0.06
    ners
    -0.06
    drivers
    -0.06
    slides
    -0.06
    POSITIVE LOGITS
    isateur
    0.07
    рез
    0.07
    аза
    0.07
    Dé
    0.07
    eldig
    0.06
    ื้
    0.06
     lø
    0.06
    _static
    0.06
    .onResume
    0.06
     ніби
    0.06
    Activations Density 0.023%

    No Known Activations