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

    Neuronpedia

    APICircuit 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. 11-RESID-POST-AA
    6. 80794
    Prev
    Next
    INDEX
    Explanations

    index

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     comfy
    -0.07
     Bullet
    -0.07
    Pod
    -0.07
    _LEN
    -0.06
     ASE
    -0.06
    integral
    -0.06
    EAR
    -0.06
    /.↵↵
    -0.06
     punched
    -0.06
    サイト
    -0.06
    POSITIVE LOGITS
    _clients
    0.06
     paints
    0.06
    Receive
    0.06
    VERTISE
    0.06
     haunted
    0.06
     withhold
    0.06
    :nth
    0.06
     announcements
    0.06
     predis
    0.06
    UIAlert
    0.06
    Activations Density 0.005%

    No Known Activations