© 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. 7363
    Prev
    Next
    INDEX
    Explanations

    letters

    np_max-act · gemini-2.0-flash

    The neuron activates on the word “letters” (in the context of “N letters picked without replacement”).

    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
    (command
    -0.07
     traumat
    -0.07
     Three
    -0.06
    son
    -0.06
     invade
    -0.06
    IONS
    -0.06
    ocations
    -0.06
    ']].
    -0.06
    landır
    -0.06
    .deep
    -0.06
    POSITIVE LOGITS
     uyum
    0.07
    LBL
    0.07
    _purchase
    0.07
     flawed
    0.06
     тест
    0.06
     oct
    0.06
     речов
    0.06
    EMP
    0.06
    _PID
    0.06
    attempt
    0.06
    Activations Density 0.001%

    No Known Activations