© 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. 56540
    Prev
    Next
    INDEX
    Explanations

    treatment

    np_max-act · gemini-2.0-flash

    information related to antibiotic treatments and their dosages.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron activates on tokens related to “treatment” (e.g. treatment, tratamiento, tratamento).

    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
     몰
    -0.07
     Zip
    -0.07
    wallet
    -0.06
    ωσε
    -0.06
    ados
    -0.06
    人員
    -0.06
    Proxy
    -0.06
     UIP
    -0.06
     Wak
    -0.06
    su
    -0.06
    POSITIVE LOGITS
     vra
    0.07
    __()↵
    0.07
    uctive
    0.07
     swo
    0.06
    wiąz
    0.06
     Spa
    0.06
     господар
    0.06
    dikleri
    0.06
     kriz
    0.06
    inner
    0.06
    Activations Density 0.017%

    No Known Activations