© 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. 7597
    Prev
    Next
    INDEX
    Explanations

    programming file extensions

    np_max-act · gemini-2.0-flash

    The neuron fires on identifiers of object‐ or instance‐level fields or properties that appear on the left side of an assignment (e.g. “this.foo = …” or “obj.field = …”).

    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
     Desire
    -0.07
     리스트
    -0.06
    KF
    -0.06
    》(
    -0.06
     Мар
    -0.06
    Nib
    -0.06
    lp
    -0.06
    NEL
    -0.06
     {}),↵
    -0.06
     Mast
    -0.06
    POSITIVE LOGITS
     Railroad
    0.06
    STRING
    0.06
     спост
    0.06
    ?option
    0.06
    	Scanner
    0.06
     soared
    0.06
    awaii
    0.06
    отв
    0.06
     Investig
    0.06
    _gamma
    0.06
    Activations Density 0.016%

    No Known Activations