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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 56791
    Prev
    Next
    INDEX
    Explanations

    celebrities

    np_max-act · gemini-2.0-flash

    The neuron activates on words and names that signal celebrities, “star” casting, or star‐studded talent listings.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    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
     VH
    -0.08
     тв
    -0.07
    剑
    -0.07
    üyle
    -0.06
     maxWidth
    -0.06
    よび
    -0.06
     Soviets
    -0.06
    stead
    -0.06
    ับส
    -0.06
     الس
    -0.06
    POSITIVE LOGITS
    uality
    0.07
     operates
    0.06
     возникнов
    0.06
    (enable
    0.06
    .goto
    0.06
     arrive
    0.06
     Phòng
    0.05
     resultSet
    0.05
     şik
    0.05
     Receive
    0.05
    Activations Density 0.190%

    No Known Activations