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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 71231
    Prev
    Next
    INDEX
    Explanations

    code

    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
     ridiculously
    -0.07
     firmly
    -0.07
     chairs
    -0.06
     discrepan
    -0.06
    modify
    -0.06
     lin
    -0.06
     fet
    -0.06
     surrounding
    -0.06
    발
    -0.06
    _qos
    -0.06
    POSITIVE LOGITS
     parler
    0.06
     attempting
    0.06
     Tantra
    0.06
    /runtime
    0.06
    َم
    0.06
     حافظ
    0.06
    .isLoggedIn
    0.06
     parch
    0.06
    /Runtime
    0.06
     ऑ
    0.06
    Activations Density 0.048%

    No Known Activations