© 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. 57080
    Prev
    Next
    INDEX
    Explanations

    Fellow/resident

    np_max-act · gemini-2.0-flash

    The neuron activates most strongly on tokens naming academic and artistic honors, fellowships, residencies, prizes, and related titles.

    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
     servi
    -0.06
    şt
    -0.06
    Loaded
    -0.06
    .PARAM
    -0.06
    สต
    -0.06
     flam
    -0.06
    levision
    -0.06
    kud
    -0.06
    cedure
    -0.06
    _cost
    -0.06
    POSITIVE LOGITS
    _Public
    0.07
     }*/↵
    0.07
     companyId
    0.07
    .Formatter
    0.07
     dur
    0.06
    ++){
    0.06
    へと
    0.06
    .velocity
    0.06
    DJ
    0.06
    trainer
    0.06
    Activations Density 0.032%

    No Known Activations