© 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 (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 126356
    Prev
    Next
    INDEX
    Explanations

    href

    np_max-act · gemini-2.0-flash

    The neuron is attuned to link constructs (anchor tags, href attributes, link variables/functions) in code.

    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
    ritch
    -0.06
    ्त
    -0.06
     Pra
    -0.06
    ตร
    -0.06
    extension
    -0.06
     UW
    -0.06
    _request
    -0.06
    年代
    -0.06
    上的
    -0.06
    _ad
    -0.06
    POSITIVE LOGITS
     Совет
    0.07
    QR
    0.07
    qr
    0.06
    _MAJOR
    0.06
    meet
    0.06
    출
    0.06
     minY
    0.06
     ек
    0.06
    .firstChild
    0.06
    "They
    0.06
    Activations Density 0.039%

    No Known Activations