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. 123689
    Prev
    Next
    INDEX
    Explanations

    political turmoil

    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
     bureaucracy
    -0.06
    __))↵
    -0.06
    els
    -0.06
     Dalton
    -0.06
    bmp
    -0.06
     rice
    -0.06
    .reverse
    -0.06
     Sisters
    -0.06
     insulation
    -0.06
     optics
    -0.06
    POSITIVE LOGITS
    -gun
    0.06
    менш
    0.06
     NI
    0.06
     CONDITIONS
    0.06
     пол
    0.06
     canv
    0.06
    -Tr
    0.06
    ổng
    0.06
    .pen
    0.06
    patterns
    0.06
    Activations Density 0.050%

    No Known Activations