© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 41487
    Prev
    Next
    INDEX
    Explanations

    Buildings

    np_max-act · gemini-2.0-flash

    The neuron fires on tokens related to talking about skyscrapers’ heights and names—especially mentions of “tallest,” “building,” “tower,” 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
     Lal
    -0.07
    ♠
    -0.07
     několik
    -0.07
    !==
    -0.06
    _rad
    -0.06
     Dion
    -0.06
    (Fl
    -0.06
    (Player
    -0.06
    There
    -0.06
     RETURNS
    -0.06
    POSITIVE LOGITS
    ').
    0.07
    .il
    0.06
    ософ
    0.06
     ").
    0.06
    Authentication
    0.06
    وان
    0.06
     ''
    0.06
     confess
    0.06
    uling
    0.06
    insic
    0.06
    Activations Density 0.024%

    No Known Activations