© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7158
    Prev
    Next
    INDEX
    Explanations

    Plus/minus signs

    np_max-act · gemini-2.0-flash

    The neuron fires on arithmetic operator tokens (e.g. “+”, “*”, etc.) in math expressions.

    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
     tý
    -0.06
    cef
    -0.06
     won
    -0.06
    �
    -0.06
     Abdul
    -0.05
    霊
    -0.05
    圈
    -0.05
    _SHORT
    -0.05
    -day
    -0.05
    Mus
    -0.05
    POSITIVE LOGITS
    ゛
    0.07
    hiba
    0.07
    омен
    0.06
    GD
    0.06
     cómo
    0.06
     \"
    0.06
    ottie
    0.06
     roulette
    0.06
    _last
    0.06
    deme
    0.06
    Activations Density 0.011%

    No Known Activations