© 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. 18269
    Prev
    Next
    INDEX
    Explanations

    terms related to cancer treatments and their effects

    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
    otlin
    -0.06
    ãĥĢãĤ¤
    -0.06
    sn
    -0.06
     DISPATCH
    -0.06
    ër
    -0.06
     GER
    -0.06
     Huffman
    -0.05
    andbox
    -0.05
    ë§IJ
    -0.05
    Ä©
    -0.05
    POSITIVE LOGITS
     chemotherapy
    0.11
    GINE
    0.08
     Cancer
    0.08
     cancer
    0.08
     platinum
    0.08
     bald
    0.07
    /MPL
    0.07
     toxicity
    0.07
    ieder
    0.07
     Platinum
    0.07
    Activations Density 0.042%

    No Known Activations