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. 80588
    Prev
    Next
    INDEX
    Explanations

    losing opportunity

    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
     Features
    -0.07
    nor
    -0.07
     succeeded
    -0.06
    ="(
    -0.06
     Done
    -0.06
     ange
    -0.06
     Feet
    -0.06
     drawback
    -0.06
    nio
    -0.06
     advises
    -0.06
    POSITIVE LOGITS
     darüber
    0.07
     Posting
    0.06
    _exempt
    0.06
     EditorGUI
    0.06
    aciente
    0.06
     squ
    0.06
     sahibi
    0.06
     صن
    0.06
    ství
    0.06
     ting
    0.06
    Activations Density 0.101%

    No Known Activations