© 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. 3-RESID-POST-AA
    6. 121924
    Prev
    Next
    INDEX
    Explanations

    >>

    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_3/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SSERT
    -0.07
     frü
    -0.06
     projektu
    -0.06
    reon
    -0.06
    जब
    -0.06
    _tab
    -0.06
     tém
    -0.06
     Randolph
    -0.06
    З
    -0.06
    ΑΠ
    -0.06
    POSITIVE LOGITS
    oblins
    0.12
     Goblin
    0.12
    oblin
    0.10
    dr
    0.08
    "+"
    0.06
    カー
    0.06
     Blow
    0.06
    ening
    0.06
    mares
    0.06
     Adjustable
    0.06
    Activations Density 0.003%

    No Known Activations