© 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. 101645
    Prev
    Next
    INDEX
    Explanations

    ages

    np_max-act · gemini-2.0-flash

    The neuron detects mentions of a character’s age expressed as a “<number>-year-old” (e.g. “12-year-old”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    content related to bondage, power dynamics, or themes of authority and submission.

    oai_token-act-pair · gpt-4o-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
    repair
    -0.07
    040
    -0.07
     charges
    -0.06
    พล
    -0.06
     charge
    -0.06
    020
    -0.06
    080
    -0.06
    lix
    -0.06
    expr
    -0.06
    fax
    -0.06
    POSITIVE LOGITS
     southwest
    0.06
     ребенок
    0.06
     geil
    0.06
     butt
    0.06
    //
↵
    0.06
     sám
    0.06
    ladı
    0.06
     vul
    0.06
    	pub
    0.05
    ा,
    0.05
    Activations Density 0.026%

    No Known Activations