© 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. 55578
    Prev
    Next
    INDEX
    Explanations

    cancer research

    np_max-act · gemini-2.0-flash

    The neuron is selectively activated by biomedical and experimental context terms—disease names, tissues/organs, and model descriptors (e.g. tumor, cancer, skin, systemic, CNS, vascular, heart, mouse, treated).

    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
     endoth
    -0.08
    -editor
    -0.07
    �
    -0.07
     prolonged
    -0.07
    owa
    -0.06
     Met
    -0.06
    ._
    -0.06
    ros
    -0.06
    adesh
    -0.06
    pred
    -0.06
    POSITIVE LOGITS
    letal
    0.07
    jah
    0.07
    <g
    0.06
    ΙΑ
    0.06
     ヾ
    0.06
    villa
    0.06
    rám
    0.06
     IsActive
    0.06
    "h
    0.06
    鄉
    0.06
    Activations Density 0.099%

    No Known Activations