© 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. 108910
    Prev
    Next
    INDEX
    Explanations

    comparisons over time/versions

    np_max-act · gemini-2.0-flash

    This neuron detects language about comparing or benchmarking performance (e.g., references to “previous,” “performance,” “against,” “own,” 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
     wed
    -0.07
     kam
    -0.07
    _le
    -0.07
    _END
    -0.06
     پنج
    -0.06
    ца
    -0.06
     scrap
    -0.06
    _props
    -0.06
     CWE
    -0.06
     окон
    -0.06
    POSITIVE LOGITS
    τερα
    0.07
    Suite
    0.06
    inge
    0.06
     Freak
    0.06
    <Expression
    0.06
    Org
    0.06
     Rene
    0.06
     ấy
    0.06
    論
    0.06
    /Instruction
    0.06
    Activations Density 0.236%

    No Known Activations