© 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. 28145
    Prev
    Next
    INDEX
    Explanations

    organ

    np_max-act · gemini-2.0-flash

    The neuron activates on the root “organ” (e.g. organ, organs, organoid, organotypic, organoids), i.e. mentions of biological organs or organ‐based terms.

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

    discussions related to organ systems, particularly in a biological and medical context.

    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
    723
    -0.08
    isiert
    -0.07
     theft
    -0.07
    ekli
    -0.07
     Carlson
    -0.07
     False
    -0.07
    き
    -0.07
    ('<
    -0.06
    Blake
    -0.06
    ;'>
    -0.06
    POSITIVE LOGITS
     organ
    0.13
     organs
    0.12
     Organ
    0.12
     Morgan
    0.11
    organ
    0.10
     органов
    0.10
    Organ
    0.09
    .organ
    0.09
     орган
    0.08
    pers
    0.08
    Activations Density 0.009%

    No Known Activations