© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 6943
    Prev
    Next
    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash

    The neuron fires on the numeric portions of long structured identifiers (e.g. the digit sequences in GUIDs/UUIDs).

    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
    hei
    -0.07
    coli
    -0.07
    僅
    -0.07
     مدیر
    -0.06
    ordes
    -0.06
    ادث
    -0.06
     Belediyesi
    -0.06
    ervoir
    -0.06
    уже
    -0.06
     exhaustive
    -0.06
    POSITIVE LOGITS
    ;;↵
    0.08
    ][]
    0.07
     {};
    0.07
    _document
    0.07
    tility
    0.06
    :auto
    0.06
    ha
    0.06
     duplicate
    0.06
     geliyor
    0.06
     ;;↵
    0.06
    Activations Density 0.004%

    No Known Activations