© 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. 56539
    Prev
    Next
    INDEX
    Explanations

    Negation, code constraints

    np_max-act · gemini-2.0-flash

    The neuron activates on instruction‐style metadata words and phrases specifying rules or constraints (e.g. “constraints,” “forbidden,” “must,” “maximum”).

    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
    <num
    -0.07
    blocked
    -0.07
    _Request
    -0.07
     prest
    -0.06
     Marion
    -0.06
     tcp
    -0.06
    egration
    -0.06
     cosplay
    -0.06
     East
    -0.06
     Rocket
    -0.06
    POSITIVE LOGITS
     faucet
    0.07
    Φ
    0.06
    áf
    0.06
    +
    0.06
    hk
    0.06
     UN
    0.06
     testim
    0.06
    .getEntity
    0.06
     Kết
    0.06
     фунда
    0.06
    Activations Density 0.029%

    No Known Activations