© 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. 126300
    Prev
    Next
    INDEX
    Explanations

    radiation dosimetry

    np_max-act · gemini-2.0-flash

    The neuron strongly activates on technical dosimetry terms—mentions of measured or calculated radiation-therapy parameters (dose values, output/correction factors, beam profiles, ionization chamber readings, etc.).

    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
    _CONNECTED
    -0.08
    ल
    -0.07
     фін
    -0.07
    MouseMove
    -0.07
     Torrent
    -0.06
     Acres
    -0.06
    644
    -0.06
    _yellow
    -0.06
    دانلود
    -0.06
    .ravel
    -0.06
    POSITIVE LOGITS
    live
    0.07
    xE
    0.06
     SIZE
    0.06
     ldb
    0.06
    _PANEL
    0.06
    _DRIVER
    0.06
    dez
    0.06
     DAM
    0.06
     şekl
    0.06
    nement
    0.06
    Activations Density 0.016%

    No Known Activations