© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 80447
    Prev
    Next
    INDEX
    Explanations

    medical terminology related to cancer and tumor progression

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ÐĶÐIJ
    -0.06
    ãĥ¬ãĤ¤
    -0.06
    CEE
    -0.06
    Reusable
    -0.06
    lio
    -0.06
     ÑĤоÑĢ
    -0.06
    !=-
    -0.06
    quests
    -0.06
    SetActive
    -0.06
     Youth
    -0.06
    POSITIVE LOGITS
     metast
    0.09
     cancer
    0.08
     Cancer
    0.07
    adir
    0.07
    elper
    0.06
     zoekt
    0.06
     cancers
    0.06
     jenter
    0.06
     tumor
    0.06
    Å¡et
    0.06
    Activations Density 0.010%

    No Known Activations