© 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. 44399
    Prev
    Next
    INDEX
    Explanations

    co

    np_max-act · gemini-2.0-flash

    The neuron fires on words that refer to organizational structure or schemes (e.g. “esquema,” “jerarquía”).

    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
     homic
    -0.07
    /pl
    -0.06
     ferment
    -0.06
     nuest
    -0.06
     landsc
    -0.06
    .det
    -0.06
    504
    -0.06
     ر
    -0.06
     fermented
    -0.06
     nale
    -0.06
    POSITIVE LOGITS
    іп
    0.07
    PY
    0.07
    vim
    0.07
    ιο
    0.06
    getEmail
    0.06
    ]):↵
    0.06
    _MOUSE
    0.06
     ^↵
    0.06
    添
    0.06
     думку
    0.06
    Activations Density 0.104%

    No Known Activations