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. 111385
    Prev
    Next
    INDEX
    Explanations

    on

    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
    ckill
    -0.07
     asia
    -0.07
    (can
    -0.07
    _IMPORTED
    -0.06
    component
    -0.06
     henne
    -0.06
     фінанс
    -0.06
     팬
    -0.06
     cheek
    -0.06
     ポ
    -0.06
    POSITIVE LOGITS
    .getString
    0.06
    аци
    0.06
    vc
    0.06
    igail
    0.06
    Actually
    0.06
    configuration
    0.06
    LEGRO
    0.06
    implement
    0.06
    طل
    0.06
     cents
    0.06
    Activations Density 0.038%

    No Known Activations