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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 56004
    Prev
    Next
    INDEX
    Explanations

    deprecation in programming

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of deprecated or obsolete functionality—words and phrases flagging that something is deprecated.

    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
    ivirus
    -0.07
    кові
    -0.06
    وغ
    -0.05
    _completion
    -0.05
    教学
    -0.05
     sprites
    -0.05
    -icon
    -0.05
     beforeSend
    -0.05
    /****************
    -0.05
    شه
    -0.05
    POSITIVE LOGITS
     пунк
    0.07
    Quote
    0.06
    (Call
    0.06
    (Create
    0.06
    >")↵
    0.06
     empowered
    0.06
     vyh
    0.06
     ime
    0.06
     wore
    0.06
     điểm
    0.06
    Activations Density 0.038%

    No Known Activations