© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 13433
    Prev
    Next
    INDEX
    Explanations

    punctuation and "and"

    np_max-act · gemini-2.0-flash

    This neuron detects instructions for routine technical troubleshooting steps (like clearing your browser cache or checking settings).

    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
    وز
    -0.07
     площ
    -0.07
     переход
    -0.07
    امل
    -0.07
     ослож
    -0.07
    Bundle
    -0.07
    اعي
    -0.06
     misguided
    -0.06
     ناحیه
    -0.06
    �
    -0.06
    POSITIVE LOGITS
    prototype
    0.06
    nP
    0.06
    antasy
    0.06
    agnosis
    0.06
    ιας
    0.06
     europ
    0.06
     куп
    0.06
    .prototype
    0.06
    ETHOD
    0.06
    _M
    0.06
    Activations Density 0.170%

    No Known Activations