© 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. 125254
    Prev
    Next
    INDEX
    Explanations

    medical research

    np_max-act · gemini-2.0-flash

    terms related to infectious diseases and their agents.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron activates on mentions of body tissues, organs, or anatomical sites (e.g. skin, respiratory tract, nasal passages, intestinal lining, kidney, etc.).

    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
     نار
    -0.07
     đem
    -0.06
     теп
    -0.06
    iasco
    -0.06
    timezone
    -0.06
     老
    -0.06
    ैठ
    -0.06
    ่าต
    -0.06
     nabíd
    -0.06
     можливість
    -0.06
    POSITIVE LOGITS
     unnatural
    0.07
     augmented
    0.07
    _VOID
    0.06
    ília
    0.06
     yönetimi
    0.06
    '|
    0.06
     corpo
    0.06
    ictured
    0.06
     Solid
    0.06
     Represent
    0.06
    Activations Density 0.026%

    No Known Activations