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. 15-RESID-POST-AA
    6. 94303
    Prev
    Next
    INDEX
    Explanations

    numerical data

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Removing
    -0.06
    /Open
    -0.06
     MsgBox
    -0.06
    _Filter
    -0.06
     Finds
    -0.06
     OnePlus
    -0.06
    vals
    -0.06
    abol
    -0.06
     přek
    -0.06
    seud
    -0.06
    POSITIVE LOGITS
     endurance
    0.07
     currently
    0.06
     figures
    0.06
    díl
    0.06
     astronom
    0.06
     traditions
    0.06
    amate
    0.06
    今
    0.06
     merchandise
    0.06
     many
    0.06
    Activations Density 0.002%

    No Known Activations