© 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. 110263
    Prev
    Next
    INDEX
    Explanations

    int

    np_max-act · gemini-2.0-flash

    The neuron responds to numeric content—digits, numeric literals, and the names of Python’s numeric types (e.g. “int,” “float”).

    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
     Wolff
    -0.07
     bundles
    -0.07
     Literature
    -0.07
    naments
    -0.06
     ornaments
    -0.06
     chemistry
    -0.06
     Quran
    -0.06
     unge
    -0.06
    _fre
    -0.06
     foil
    -0.06
    POSITIVE LOGITS
    [source
    0.08
    -inter
    0.07
    지고
    0.07
    (question
    0.07
    ivariate
    0.06
    (rs
    0.06
    elsey
    0.06
    _tA
    0.06
    difference
    0.06
     kvinne
    0.06
    Activations Density 0.024%

    No Known Activations