© 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. 90752
    Prev
    Next
    INDEX
    Explanations

    stem

    np_max-act · gemini-2.0-flash

    The neuron detects mentions of hematopoietic stem cells (e.g., “hematopoietic stem cell” or related phrasing).

    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
     Ere
    -0.07
     OWN
    -0.06
    üçük
    -0.06
     prisons
    -0.06
     Müdürlüğü
    -0.06
    하고
    -0.06
     ayak
    -0.06
     Framework
    -0.06
     buckets
    -0.06
     immediate
    -0.06
    POSITIVE LOGITS
     Libert
    0.08
    πος
    0.06
     nes
    0.06
    )findViewById
    0.06
    ,list
    0.06
    (stock
    0.06
    填
    0.06
     unaware
    0.06
    (shape
    0.06
    (im
    0.06
    Activations Density 0.002%

    No Known Activations