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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 55843
    Prev
    Next
    INDEX
    Explanations

    elegans

    np_max-act · gemini-2.0-flash

    The neuron activates on references to the nematode model organism Caenorhabditis elegans (including its common name “worm”).

    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
     Wor
    -0.07
     Bor
    -0.07
    isti
    -0.06
    Mil
    -0.06
     тобто
    -0.06
     муз
    -0.06
     Owens
    -0.06
    th
    -0.06
    chemistry
    -0.06
    gps
    -0.06
    POSITIVE LOGITS
    (suffix
    0.08
    (){↵
    0.07
     transl
    0.07
    (hour
    0.06
     жест
    0.06
    {↵
    0.06
     eleg
    0.06
    一般
    0.06
    VG
    0.06
    (option
    0.06
    Activations Density 0.000%

    No Known Activations