Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 85023
    Prev
    Next
    INDEX
    Explanations

    neck

    np_max-act · gemini-2.0-flash

    The main thing this neuron does is detect mentions of specific anatomical structures or locations in medical text.

    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
     matches
    -0.07
    _wo
    -0.06
    'al
    -0.06
    .Unit
    -0.06
    .lastname
    -0.06
    ?',↵
    -0.06
    externalActionCode
    -0.06
     enjo
    -0.06
    ücken
    -0.06
     สพ
    -0.06
    POSITIVE LOGITS
     sty
    0.06
    //(
    0.06
    τίου
    0.06
    技术
    0.06
     centro
    0.06
    ‌خ
    0.06
    izzie
    0.06
    भ
    0.06
     yield
    0.06
    厅
    0.06
    Activations Density 0.018%

    No Known Activations