© 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. 89562
    Prev
    Next
    INDEX
    Explanations

    Food or community events

    np_max-act · gemini-2.0-flash

    The neuron detects names of events or festivals (multiword capitalized titles like “Soup for the Soul,” “Oyster and Beer Festival,” “Tour de Chocolate,” etc.).

    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
     DN
    -0.07
     eerie
    -0.07
    .tem
    -0.07
    -ton
    -0.07
     conferred
    -0.06
     cref
    -0.06
     Ly
    -0.06
    "data
    -0.06
    };↵
    -0.06
     hormones
    -0.06
    POSITIVE LOGITS
    rypto
    0.06
    <option
    0.06
    liches
    0.06
    บร
    0.06
     pro
    0.06
    -aff
    0.06
     panels
    0.06
    ────────
    0.06
    패
    0.06
    omm
    0.06
    Activations Density 0.045%

    No Known Activations