© 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. 130155
    Prev
    Next
    INDEX
    Explanations

    questions

    np_max-act · gemini-2.0-flash

    This neuron activates on JSON-style structural tokens and placeholders (e.g., “#OPTIONS,” “#FILLME,” braces, and other template key markers).

    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
    _trials
    -0.06
    Cele
    -0.06
     hvě
    -0.06
     methodName
    -0.06
     Mate
    -0.06
     clr
    -0.06
    design
    -0.06
     اد
    -0.06
    (SE
    -0.06
     dopl
    -0.06
    POSITIVE LOGITS
     Kostenlos
    0.07
    К
    0.07
    -checkbox
    0.07
    ÅŸ
    0.06
    urtles
    0.06
    setFlash
    0.06
     luôn
    0.06
    Russian
    0.06
    yh
    0.06
     staging
    0.06
    Activations Density 0.307%

    No Known Activations