© 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
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 41498
    Prev
    Next
    INDEX
    Explanations

    Pheochromocytoma/paraganglioma

    np_max-act · gemini-2.0-flash

    The neuron selectively fires on occurrences of the substring “MAO” (as in MAO inhibitors) and on the “ochrom” element in words like pheochromocytoma.

    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
    ıs
    -0.06
    اذا
    -0.06
    home
    -0.06
     Bat
    -0.06
     Peb
    -0.06
    ło
    -0.06
    ":{↵
    -0.06
    firstname
    -0.06
     }(
    -0.06
    Paint
    -0.06
    POSITIVE LOGITS
    做
    0.08
    100
    0.07
    酸
    0.06
    noinspection
    0.06
     bye
    0.06
    ope
    0.06
     Code
    0.06
     tonnes
    0.06
    ervatives
    0.06
     <%=
    0.06
    Activations Density 0.001%

    No Known Activations