© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 78190
    Prev
    Next
    INDEX
    Explanations

    CRT

    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
    ่อ
    -0.07
    ()).
    -0.07
    -sharing
    -0.07
    _ORIGIN
    -0.06
    _contr
    -0.06
    С
    -0.06
     حسب
    -0.06
    CORE
    -0.06
    \Admin
    -0.06
    _Ad
    -0.06
    POSITIVE LOGITS
     intox
    0.07
    jwt
    0.06
     viele
    0.06
    ��
    0.06
    ebiliriz
    0.06
    ücret
    0.06
     researching
    0.06
     شخصیت
    0.06
    (vars
    0.06
     Crus
    0.06
    Activations Density 0.003%

    No Known Activations