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. 11-RESID-POST-AA
    6. 74884
    Prev
    Next
    INDEX
    Explanations

    equations

    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
    никами
    -0.07
     unordered
    -0.07
    DataSet
    -0.06
     defender
    -0.06
    /unit
    -0.06
    _HASH
    -0.06
    _repr
    -0.06
     puppy
    -0.06
    디
    -0.06
     LED
    -0.06
    POSITIVE LOGITS
     zg
    0.07
     白
    0.06
     матери
    0.06
    ูช
    0.06
     برق
    0.06
    스의
    0.06
     athletic
    0.06
     ğ
    0.05
     khác
    0.05
     Napoli
    0.05
    Activations Density 0.014%

    No Known Activations