© 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. 58425
    Prev
    Next
    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash

    The neuron is strongly activated by words naming specific mechanical or technical components (e.g. spacer, shim, compression ring, plate, winglet, deflector, shield).

    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
     сентября
    -0.07
     Over
    -0.07
     MyApp
    -0.06
    외
    -0.06
     timeStamp
    -0.06
     PM
    -0.06
    Description
    -0.06
     promising
    -0.06
     NOTE
    -0.06
     Rif
    -0.06
    POSITIVE LOGITS
     معماری
    0.07
    (hdc
    0.07
     jednotlivých
    0.07
    街道
    0.07
    .FALSE
    0.06
    mounted
    0.06
    ув
    0.06
    ηση
    0.06
    ndl
    0.06
    ера
    0.06
    Activations Density 0.086%

    No Known Activations