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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 11-RESID-POST-AA
    6. 26075
    Prev
    Next
    INDEX
    Explanations

    product specifications/reviews

    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
    _exec
    -0.06
     лет
    -0.06
     ReturnType
    -0.06
    oglobin
    -0.06
    .access
    -0.06
    िए
    -0.06
    ored
    -0.06
     термін
    -0.06
     goggles
    -0.06
    IpAddress
    -0.06
    POSITIVE LOGITS
     unintention
    0.07
     liter
    0.07
    _##
    0.06
     COMPLETE
    0.06
    ợ
    0.06
     اندازه
    0.06
     돈
    0.06
    _Re
    0.06
     taille
    0.06
    *(
    0.06
    Activations Density 0.039%

    No Known Activations