© 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. 38734
    Prev
    Next
    INDEX
    Explanations

    electrons

    np_max-act · gemini-2.0-flash

    The neuron activates on occurrences of “electron” (and its plural)—i.e. mentions of electrons or related charged‐particle/electrical concepts.

    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
     theories
    -0.06
    -leg
    -0.06
     hypotheses
    -0.06
     Airways
    -0.06
    υγ
    -0.06
     sunrise
    -0.06
     Managers
    -0.06
    agar
    -0.06
    renal
    -0.06
     sensations
    -0.06
    POSITIVE LOGITS
    .float
    0.07
    μάτων
    0.07
    \controllers
    0.07
    Workspace
    0.07
     -*-
    0.07
    manı
    0.07
     uint
    0.07
    结束
    0.07
    appable
    0.07
     QColor
    0.06
    Activations Density 0.009%

    No Known Activations