Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 20184
    Prev
    Next
    INDEX
    Explanations

    to

    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
    =l
    -0.07
    Transformation
    -0.07
     Nature
    -0.06
    Hat
    -0.06
    Fat
    -0.06
     Hearth
    -0.06
     jeux
    -0.06
    ไฟล
    -0.06
     dependencies
    -0.06
    °}
    -0.06
    POSITIVE LOGITS
     Dining
    0.07
    buie
    0.07
     requiring
    0.06
     accordingly
    0.06
    (first
    0.06
     ');
    0.06
    ισ
    0.06
     مد
    0.06
    产
    0.06
     chiếc
    0.06
    Activations Density 0.011%

    No Known Activations