© 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
    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. 7069
    Prev
    Next
    INDEX
    Explanations

    value

    np_max-act · gemini-2.0-flash

    The neuron fires on occurrences of terms related to “eigenvalues” (and closely associated eigen– vocabulary).

    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
     mobs
    -0.07
    pert
    -0.06
    _figure
    -0.06
    raction
    -0.06
     Dinner
    -0.06
     biệt
    -0.06
     LinkedIn
    -0.06
    、『
    -0.06
    官网
    -0.06
     din
    -0.06
    POSITIVE LOGITS
    ाव
    0.07
     ALSO
    0.07
    Statistics
    0.07
     Прав
    0.07
    value
    0.06
     симптомы
    0.06
    -Л
    0.06
    ingleton
    0.06
    Slots
    0.06
    rays
    0.06
    Activations Density 0.002%

    No Known Activations