Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 123135
    Prev
    Next
    INDEX
    Explanations

    it

    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
    Stick
    -0.06
    ":[{"
    -0.06
     Municipal
    -0.06
     Sandbox
    -0.06
     mouseClicked
    -0.06
     underground
    -0.06
     TextArea
    -0.06
    로는
    -0.06
    .configure
    -0.06
     Regional
    -0.06
    POSITIVE LOGITS
    フィ
    0.07
    />";↵
    0.06
    MBOL
    0.06
    τός
    0.06
    لام
    0.06
     brushing
    0.06
    Cam
    0.06
    Detalle
    0.06
    榜
    0.06
     collage
    0.06
    Activations Density 0.068%

    No Known Activations