© 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 EvalsExportsinterp-engineNEWAPI 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. 58831
    Prev
    Next
    INDEX
    Explanations

    historical artifacts

    np_max-act · gemini-2.0-flash

    This neuron activates on nouns naming physical archaeological finds and related artefacts (e.g. tools, tombs, pottery, sculptures, nails, forts).

    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
     Hundreds
    -0.07
     đòi
    -0.07
     �
    -0.06
    OLEAN
    -0.06
    >>();↵
    -0.06
     BACKGROUND
    -0.06
     багат
    -0.06
    >\
    -0.06
     >>
    -0.06
     signer
    -0.06
    POSITIVE LOGITS
     organic
    0.07
    cntl
    0.06
     FOOD
    0.06
     الخ
    0.06
    pais
    0.06
    mnt
    0.06
     prejudices
    0.06
    枝
    0.06
    \Backend
    0.06
     TF
    0.06
    Activations Density 0.023%

    No Known Activations