© 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. 62263
    Prev
    Next
    INDEX
    Explanations

    terms related to cancer, specifically types and classifications of sarcoma

    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
    ubi
    -0.07
    itches
    -0.07
    áme
    -0.07
    .dtd
    -0.07
    _dyn
    -0.07
    æļĹ
    -0.07
    isman
    -0.07
    lient
    -0.07
    bak
    -0.07
    night
    -0.06
    POSITIVE LOGITS
     cancer
    0.07
     Mes
    0.07
     mes
    0.07
     Cancer
    0.06
    Mes
    0.06
    .neo
    0.06
     port
    0.06
    ets
    0.06
    edBy
    0.05
     gro
    0.05
    Activations Density 0.000%

    No Known Activations