© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 54546
    Prev
    Next
    INDEX
    Explanations

    post-mitotic neurons

    np_max-act · gemini-2.0-flash

    The neuron activates on words and phrases that indicate a cell’s division status—especially “mitotic,” “post-mitotic,” or related proliferation terms.

    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
     Og
    -0.07
    「お
    -0.07
    草
    -0.07
     quý
    -0.07
    ampil
    -0.07
     Nancy
    -0.07
    :$
    -0.07
    `).
    -0.06
    _crop
    -0.06
    .Field
    -0.06
    POSITIVE LOGITS
     ImGui
    0.08
    imedia
    0.07
     ISIS
    0.07
    μένοι
    0.06
     mit
    0.06
     président
    0.06
    edImage
    0.06
     họp
    0.06
     directs
    0.06
    .Many
    0.06
    Activations Density 0.003%

    No Known Activations