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. 53881
    Prev
    Next
    INDEX
    Explanations

    residency

    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
    (number
    -0.07
     objects
    -0.07
     pointing
    -0.07
    ิยม
    -0.07
    calling
    -0.07
     flag
    -0.06
     flips
    -0.06
    Used
    -0.06
    Avg
    -0.06
     symbol
    -0.06
    POSITIVE LOGITS
     onCreate
    0.07
    .gstatic
    0.07
    mobx
    0.07
    Residents
    0.07
    Dam
    0.07
    GRES
    0.07
    avern
    0.07
     resides
    0.06
     Респ
    0.06
     znaj
    0.06
    Activations Density 0.088%

    No Known Activations