© 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. 30807
    Prev
    Next
    INDEX
    Explanations

    children

    np_max-act · gemini-2.0-flash

    The neuron is tuned to spot distribution-or scope-marking prepositions (e.g. “across,” “among,” “between,” “based on,” etc.) that indicate how numbers or quantities are spread or framed.

    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
     حسن
    -0.07
     Aub
    -0.07
    FIELDS
    -0.06
     ملت
    -0.06
    UpdatedAt
    -0.06
    Exec
    -0.06
     أعلام
    -0.06
    vironments
    -0.06
     Berkeley
    -0.06
     wraps
    -0.06
    POSITIVE LOGITS
    .providers
    0.06
    Timer
    0.06
     dnů
    0.06
     +:+
    0.06
    羽
    0.06
     jit
    0.06
    电脑
    0.06
     ec
    0.06
    ;">
    0.06
     spontaneously
    0.06
    Activations Density 0.091%

    No Known Activations