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. 129405
    Prev
    Next
    INDEX
    Explanations

    biological fluids

    np_max-act · gemini-2.0-flash

    The neuron detects mentions of laboratory assay measurements in bodily fluids (e.g. serum, plasma, urinary levels).

    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
    ocabulary
    -0.07
    мами
    -0.07
    _debug
    -0.06
    UPPORTED
    -0.06
     Dark
    -0.06
     THAN
    -0.06
    APTER
    -0.06
    Connecting
    -0.06
    .version
    -0.06
    .Pop
    -0.06
    POSITIVE LOGITS
    (chalk
    0.07
    //
    0.06
    lijke
    0.06
    reshape
    0.06
    ystick
    0.06
    -video
    0.06
    rega
    0.06
     Κυ
    0.06
     weeds
    0.06
     ما
    0.06
    Activations Density 0.014%

    No Known Activations