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. 88634
    Prev
    Next
    INDEX
    Explanations

    focusing on one

    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
    emia
    -0.07
    Tasks
    -0.07
    /project
    -0.06
     Snyder
    -0.06
    ін
    -0.06
    =min
    -0.06
    Thr
    -0.06
     элек
    -0.06
    inals
    -0.06
     Thr
    -0.06
    POSITIVE LOGITS
     Related
    0.07
     Choice
    0.07
    _CHO
    0.06
     East
    0.06
    mysqli
    0.06
     آنلاین
    0.06
     opt
    0.06
     reflect
    0.06
     meant
    0.06
     Agricult
    0.06
    Activations Density 0.044%

    No Known Activations