© 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. 11-RESID-POST-AA
    6. 20917
    Prev
    Next
    INDEX
    Explanations

    Inheritance

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    스트
    -0.08
     Urs
    -0.07
    Scene
    -0.07
     Clock
    -0.07
     Woche
    -0.07
    CTOR
    -0.07
    _FIRST
    -0.07
    _RX
    -0.07
     Reminder
    -0.06
     佛
    -0.06
    POSITIVE LOGITS
     ugly
    0.06
    گری
    0.06
     sorun
    0.06
     sinful
    0.06
    #w
    0.06
     buoy
    0.06
    docker
    0.06
    mc
    0.05
    サイズ
    0.05
     органів
    0.05
    Activations Density 0.006%

    No Known Activations