© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 111888
    Prev
    Next
    INDEX
    Explanations

    ri

    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
    _schedule
    -0.08
    imos
    -0.07
    hydrate
    -0.06
     add
    -0.06
     uncomment
    -0.06
    LineEdit
    -0.06
     Income
    -0.06
     Carla
    -0.06
     olarak
    -0.06
     aujourd
    -0.06
    POSITIVE LOGITS
     Tam
    0.06
    ешь
    0.06
     sewer
    0.06
     damp
    0.06
    emailer
    0.06
     قي
    0.06
    Tam
    0.06
    -zone
    0.06
     wiping
    0.06
     truth
    0.06
    Activations Density 0.003%

    No Known Activations