© 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. 44676
    Prev
    Next
    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash

    This neuron never activates—it doesn’t detect or respond to any token patterns.

    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
     каждый
    -0.06
     spaces
    -0.06
    iso
    -0.06
    ско
    -0.06
     nationalism
    -0.06
    shouldBe
    -0.06
     JComboBox
    -0.06
     battalion
    -0.06
    كو
    -0.06
    ジョ
    -0.06
    POSITIVE LOGITS
     snork
    0.07
    orch
    0.06
    VIP
    0.06
    }<
    0.06
     Drone
    0.06
            ↵        ↵
    0.06
    citation
    0.06
    Feels
    0.06
     Armour
    0.06
     Lifestyle
    0.06
    Activations Density 0.017%

    No Known Activations