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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 41306
    Prev
    Next
    INDEX
    Explanations

    gender and sexuality

    np_max-act · gemini-2.0-flash

    The neuron activates on words and prefixes related to transgender identity and topics (e.g., “transgender,” “transsexual,” “transitioning”).

    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
     NOTIFY
    -0.07
     lawy
    -0.06
    +'
    -0.06
     Hunt
    -0.06
     intimidation
    -0.06
    _CONSOLE
    -0.06
    it
    -0.06
     Elliot
    -0.06
     gef
    -0.06
     плод
    -0.06
    POSITIVE LOGITS
     transgender
    0.11
    .fn
    0.07
    ,I
    0.07
    -sizing
    0.07
     finer
    0.07
    νον
    0.07
    �
    0.06
    /trans
    0.06
    Dear
    0.06
    -direction
    0.06
    Activations Density 0.006%

    No Known Activations