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. 80700
    Prev
    Next
    INDEX
    Explanations

    Mixed content

    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
    �
    -0.08
     Giới
    -0.07
    :min
    -0.07
     مم
    -0.07
    .fm
    -0.07
    _abs
    -0.07
    .getInt
    -0.07
     kiểu
    -0.06
     الام
    -0.06
    _EQUAL
    -0.06
    POSITIVE LOGITS
     Aerospace
    0.07
    (est
    0.07
     systematic
    0.06
    freq
    0.06
     Messiah
    0.06
     singer
    0.06
     portal
    0.06
     commitments
    0.06
     desi
    0.06
     nation
    0.06
    Activations Density 0.627%

    No Known Activations