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. 95122
    Prev
    Next
    INDEX
    Explanations

    software licenses

    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
    .EntityManager
    -0.06
    (크기
    -0.06
    pha
    -0.06
    _gid
    -0.06
     birlikte
    -0.06
    uyordu
    -0.06
    finder
    -0.06
    ाभ
    -0.06
     mænd
    -0.06
     Gram
    -0.06
    POSITIVE LOGITS
     incentiv
    0.06
     Trinidad
    0.06
    Narr
    0.06
    piel
    0.06
     hazardous
    0.06
     tackle
    0.06
    .pat
    0.06
     tad
    0.06
     crunchy
    0.06
    éré
    0.06
    Activations Density 0.000%

    No Known Activations