© 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 EvalsExportsinterp-engineNEWAPI 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. 39188
    Prev
    Next
    INDEX
    Explanations

    Job titles

    np_max-act · gemini-2.0-flash

    This neuron activates on words denoting people’s formal roles or job titles (e.g., instructor, principal, coach, CEO, president).

    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
     Deg
    -0.07
     Diet
    -0.06
     values
    -0.06
    能源
    -0.06
     strangely
    -0.06
    _FRE
    -0.06
    ژ
    -0.06
    илання
    -0.06
     Aber
    -0.06
    Creates
    -0.06
    POSITIVE LOGITS
    vincia
    0.07
    .Horizontal
    0.07
     survey
    0.07
     xã
    0.07
    (Controller
    0.06
    _delta
    0.06
    ForeColor
    0.06
    ButtonDown
    0.06
    ]={
    0.06
    ّا
    0.06
    Activations Density 0.074%

    No Known Activations