© 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. 41171
    Prev
    Next
    INDEX
    Explanations

    -

    np_max-act · gemini-2.0-flash

    This neuron detects references to technical standards by spotting their alphanumeric identifiers (e.g. ISO/IEC document numbers with digits, slashes, and dashes).

    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
     Blessed
    -0.07
    .DAY
    -0.07
    .Fields
    -0.07
    rances
    -0.07
    acciones
    -0.07
     τα
    -0.07
    ホテル
    -0.07
     getC
    -0.06
    ivities
    -0.06
     Favorite
    -0.06
    POSITIVE LOGITS
    .getConfig
    0.06
    Eng
    0.06
    िभ
    0.06
    abase
    0.06
    摩
    0.06
    getConfig
    0.06
     aug
    0.06
    děl
    0.06
    许
    0.06
    กร
    0.06
    Activations Density 0.010%

    No Known Activations