© 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. 68615
    Prev
    Next
    INDEX
    Explanations

    bacteria

    np_max-act · gemini-2.0-flash

    The neuron activates on mentions of “obligate intracellular” (typically in reference to obligate intracellular bacteria or pathogens).

    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
     pojist
    -0.07
    .shopping
    -0.07
    독
    -0.07
     나라
    -0.06
     Noir
    -0.06
     Batman
    -0.06
    .argsort
    -0.06
     Sunny
    -0.06
    \Redirect
    -0.06
    SectionsIn
    -0.06
    POSITIVE LOGITS
    ademic
    0.07
     aliment
    0.07
    declaring
    0.06
    adult
    0.06
    att
    0.06
    yer
    0.06
    athlete
    0.06
    away
    0.06
    igmat
    0.06
    obe
    0.06
    Activations Density 0.003%

    No Known Activations