© 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. 58422
    Prev
    Next
    INDEX
    Explanations

    opause

    np_max-act · gemini-2.0-flash

    This neuron selectively activates on terms and phrases referring to menopause and its related physiological transition (e.g., “menopause,” “climacteric,” “hot flushes”).

    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
    igg
    -0.08
     Protestant
    -0.07
    following
    -0.07
    医疗
    -0.06
    itt
    -0.06
     Leg
    -0.06
    ziej
    -0.06
    icated
    -0.06
     walked
    -0.06
     meticulous
    -0.06
    POSITIVE LOGITS
     süt
    0.08
    덤프
    0.08
    만원입니다
    0.07
    opause
    0.07
    _ov
    0.07
    τωση
    0.07
    Mi
    0.06
     Apocalypse
    0.06
     bulls
    0.06
    ˜
    0.06
    Activations Density 0.002%

    No Known Activations