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. 105903
    Prev
    Next
    INDEX
    Explanations

    Reaching a destination

    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
     директор
    -0.06
     Avengers
    -0.06
     tracking
    -0.06
    nowrap
    -0.06
     amph
    -0.06
    chemy
    -0.06
    われる
    -0.06
     charakter
    -0.06
    іки
    -0.06
    )",
    ↵
    -0.06
    POSITIVE LOGITS
    Response
    0.07
    _HELPER
    0.06
    Classification
    0.06
    ContentSize
    0.06
     But
    0.06
     doit
    0.06
     debugger
    0.06
     перер
    0.06
    updating
    0.06
     �
    0.06
    Activations Density 0.008%

    No Known Activations