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. 87081
    Prev
    Next
    INDEX
    Explanations

    prepositions

    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
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    orpion
    -0.08
     Helvetica
    -0.07
    Na
    -0.07
     Nodes
    -0.07
    Fun
    -0.07
    oen
    -0.06
    /Login
    -0.06
     didSelect
    -0.06
    ува
    -0.06
    emain
    -0.06
    POSITIVE LOGITS
     Partisi
    0.06
     dapat
    0.06
    \\\\
    0.06
     дії
    0.06
    يكا
    0.06
     --------↵
    0.06
    ichael
    0.06
     trực
    0.06
     seated
    0.06
     Calgary
    0.06
    Activations Density 0.240%

    No Known Activations