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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 35362
    Prev
    Next
    INDEX
    Explanations

    love

    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
     drawings
    -0.06
    κτη
    -0.06
    (float
    -0.06
    anter
    -0.06
    ghan
    -0.06
     iterations
    -0.06
     ejercicio
    -0.06
    Disk
    -0.06
     Floors
    -0.06
     ihr
    -0.06
    POSITIVE LOGITS
     Love
    0.08
     love
    0.08
     místa
    0.07
     рік
    0.07
    asmine
    0.07
    -present
    0.07
     LOVE
    0.07
     taped
    0.07
     amour
    0.07
     Applicants
    0.07
    Activations Density 0.024%

    No Known Activations