© 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. 104783
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to cancer research and treatment mechanisms

    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
    ево
    -0.07
    arti
    -0.07
     dek
    -0.07
    vfs
    -0.06
    ÙĪÙĨÙĬ
    -0.06
     Bulg
    -0.06
     Oliv
    -0.06
    åĢī
    -0.06
    Toe
    -0.06
    enant
    -0.06
    POSITIVE LOGITS
     cancer
    0.13
     Cancer
    0.13
     tum
    0.11
     tumor
    0.11
    otherapy
    0.10
     targeting
    0.09
     chemotherapy
    0.09
     therapy
    0.08
     killing
    0.08
     tumors
    0.08
    Activations Density 0.014%

    No Known Activations