© 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. 57461
    Prev
    Next
    INDEX
    Explanations

    insemination

    np_max-act · gemini-2.0-flash

    The neuron activates strongly on words and word fragments related to “insemination” (including its variants and the abbreviation AI).

    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
    apeut
    -0.07
     Пет
    -0.06
     pisc
    -0.06
    dist
    -0.06
     adulthood
    -0.06
     Pandora
    -0.06
     pendant
    -0.06
     Lid
    -0.06
     Sto
    -0.06
     complications
    -0.06
    POSITIVE LOGITS
    >');
    0.07
    _checkbox
    0.07
    jian
    0.07
     groupName
    0.07
    σε
    0.07
     blatantly
    0.06
     DCHECK
    0.06
    >'.
    0.06
     Bless
    0.06
     encoded
    0.06
    Activations Density 0.003%

    No Known Activations