© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 32184
    Prev
    Next
    INDEX
    Explanations

    M

    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
     reprodu
    -0.06
    结
    -0.06
     provocative
    -0.06
    ?$
    -0.06
     because
    -0.06
     Reason
    -0.06
    .Classes
    -0.06
     Detector
    -0.06
    -windows
    -0.06
     cartoons
    -0.06
    POSITIVE LOGITS
     opioids
    0.07
     Ebony
    0.07
     멀
    0.07
     افت
    0.06
    apolis
    0.06
    alon
    0.06
    σκευή
    0.06
    土地
    0.06
    cription
    0.06
    stacle
    0.06
    Activations Density 0.139%

    No Known Activations