© 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. 57868
    Prev
    Next
    INDEX
    Explanations

    virus infecting cells

    np_max-act · gemini-2.0-flash

    The neuron activates on terms describing biological host–pathogen or cell–virus interactions—words related to infection, transmission, or cellular targeting.

    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
    opal
    -0.06
    IH
    -0.06
    _Metadata
    -0.06
    zkum
    -0.06
     Dum
    -0.06
     thirst
    -0.06
     Cary
    -0.06
     Saul
    -0.06
    Ing
    -0.06
     Yar
    -0.06
    POSITIVE LOGITS
     dern
    0.07
    Higher
    0.07
    Addr
    0.07
     قاب
    0.06
     bo
    0.06
     extra
    0.06
     pickerView
    0.06
    _est
    0.06
    ologia
    0.06
     unnecessary
    0.06
    Activations Density 0.013%

    No Known Activations