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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 58882
    Prev
    Next
    INDEX
    Explanations

    normal

    np_max-act · gemini-2.0-flash

    The neuron fires on the word “normal” when it appears as a key or label (e.g. in style or state definitions).

    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
    andan
    -0.07
    şiv
    -0.07
    	len
    -0.07
    илання
    -0.07
    olan
    -0.07
    GPC
    -0.07
    sahuje
    -0.07
    ao
    -0.07
    dados
    -0.07
     Ryu
    -0.06
    POSITIVE LOGITS
    ,label
    0.07
    ifers
    0.06
    mojom
    0.06
    搜索
    0.06
     SETTINGS
    0.06
    daf
    0.06
    ﺮ
    0.06
     forgiveness
    0.06
     دخ
    0.05
    \/\/
    0.05
    Activations Density 0.005%

    No Known Activations