© 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. 44858
    Prev
    Next
    INDEX
    Explanations

    Technology

    np_max-act · gemini-2.0-flash

    The neuron fires on verbs that describe core software operations or processing actions (e.g., “resolve,” “creates,” “deletes,” “analyzes,” “overlayed,” “calculating”).

    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
    _ends
    -0.07
    (stats
    -0.07
    _used
    -0.07
    Idx
    -0.07
     бюдж
    -0.07
    асс
    -0.07
     boiled
    -0.06
     CZ
    -0.06
    λόγ
    -0.06
    markdown
    -0.06
    POSITIVE LOGITS
    arget
    0.07
     Çağ
    0.06
     health
    0.06
    reactstrap
    0.06
    ätze
    0.06
    ()));↵
    0.06
     searcher
    0.06
    ({↵
    0.06
     africa
    0.06
     pož
    0.06
    Activations Density 0.109%

    No Known Activations