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. 21155
    Prev
    Next
    INDEX
    Explanations

    Legal citations

    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
    imgs
    -0.06
    -[
    -0.06
    schedule
    -0.06
    _Se
    -0.06
    Message
    -0.06
    Az
    -0.06
    eriod
    -0.06
    (LayoutInflater
    -0.06
    cona
    -0.06
     DAG
    -0.06
    POSITIVE LOGITS
    overlay
    0.08
    .Scale
    0.06
    /st
    0.06
     المغرب
    0.06
     urč
    0.06
     suspicions
    0.06
     indo
    0.05
     kra
    0.05
     possession
    0.05
    ạn
    0.05
    Activations Density 0.006%

    No Known Activations