© 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. 7315
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions

    np_max-act · gemini-2.0-flash

    This neuron fires on inline mathematical expressions specifying field sizes or parameters—especially occurrences of “q,” “p,” and related numeric formulas in LaTeX math mode.

    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
    mesini
    -0.07
    breaker
    -0.06
     bilgileri
    -0.06
     Gary
    -0.06
     Frozen
    -0.06
     Lydia
    -0.06
    _yellow
    -0.06
    ?>">↵
    -0.06
    ові
    -0.06
     Ry
    -0.06
    POSITIVE LOGITS
    اة
    0.07
    .Al
    0.06
    ings
    0.06
    ivos
    0.06
     ev
    0.06
     Publication
    0.06
    -economic
    0.06
     Secondly
    0.06
     Carson
    0.06
     bicy
    0.06
    Activations Density 0.004%

    No Known Activations