© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 2001
    Prev
    Next
    INDEX
    Explanations

    positive/negative situations

    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
    parsed
    -0.07
    	Local
    -0.06
     klas
    -0.06
    /ioutil
    -0.06
     tighter
    -0.06
    Road
    -0.06
    _notifications
    -0.06
     tím
    -0.06
     SCRIPT
    -0.06
    ador
    -0.06
    POSITIVE LOGITS
     içi
    0.07
     architectural
    0.06
     ACCEPT
    0.06
     MÜ
    0.06
     '=',
    0.06
     बनन
    0.06
     rises
    0.06
     органі
    0.06
     profile
    0.06
     anxiety
    0.06
    Activations Density 0.030%

    No Known Activations