© 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. 38619
    Prev
    Next
    INDEX
    Explanations

    therapy/treatment

    np_max-act · gemini-2.0-flash

    The neuron fires on mentions of therapy and mental‐health treatment contexts (e.g. “therapist,” “therapy,” “psychiatrist,” “therapeutic”).

    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
    _ioctl
    -0.07
     banker
    -0.06
    stadt
    -0.06
     Ship
    -0.06
     nuevo
    -0.06
     List
    -0.06
    Call
    -0.06
     Facts
    -0.06
    system
    -0.06
     Constraints
    -0.06
    POSITIVE LOGITS
    ozilla
    0.08
     therapist
    0.07
     wyn
    0.07
    -sp
    0.07
     індив
    0.07
    ل
    0.07
    },↵↵
    0.07
    .swagger
    0.06
    Writable
    0.06
    -this
    0.06
    Activations Density 0.019%

    No Known Activations