© 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. 126115
    Prev
    Next
    INDEX
    Explanations

    .csv

    np_max-act · gemini-2.0-flash

    The neuron activates on references to reading CSV‐based data frames in code (e.g. pandas “read_csv” calls and associated filename tokens).

    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
     Jad
    -0.07
     Tablet
    -0.07
     study
    -0.06
     بو
    -0.06
    idea
    -0.06
    jezd
    -0.06
     parametro
    -0.06
    ล
    -0.06
     Anat
    -0.06
    -panel
    -0.06
    POSITIVE LOGITS
     vbox
    0.07
     ener
    0.07
    (docs
    0.06
    .overflow
    0.06
     Ger
    0.06
     BİR
    0.06
     qreal
    0.06
    _cre
    0.06
    .getResources
    0.06
    .priority
    0.06
    Activations Density 0.019%

    No Known Activations