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. 53677
    Prev
    Next
    INDEX
    Explanations

    programming code

    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
     lawn
    -0.07
     kıy
    -0.07
     ('
    -0.07
    remove
    -0.06
    UCKET
    -0.06
     stencil
    -0.06
     Ampl
    -0.06
    /sh
    -0.06
    ước
    -0.06
    Nullable
    -0.06
    POSITIVE LOGITS
    DevExpress
    0.06
    /&
    0.06
    edad
    0.06
     링크
    0.06
     betray
    0.06
     스포츠
    0.06
     Perc
    0.06
    DownList
    0.06
    /class
    0.06
    URLException
    0.05
    Activations Density 0.164%

    No Known Activations