© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 37955
    Prev
    Next
    INDEX
    Explanations

    Code punctuation

    np_max-act · gemini-2.0-flash

    This neuron detects chained calls accessing operator inputs/outputs—e.g. sequences like op_desc.Input("…").front() or op_desc.Output("…").front().

    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
     이벤트
    -0.07
     playwright
    -0.07
    停止
    -0.07
     záznam
    -0.06
    Independent
    -0.06
    Test
    -0.06
    Thousands
    -0.06
    _high
    -0.06
    pressed
    -0.06
    _SKIP
    -0.06
    POSITIVE LOGITS
     明
    0.06
     gerade
    0.06
     asks
    0.06
     persisted
    0.06
    missible
    0.06
     mage
    0.06
    уется
    0.06
     ‏
    0.06
    ureka
    0.06
     изб
    0.05
    Activations Density 0.009%

    No Known Activations