© 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. 105147
    Prev
    Next
    INDEX
    Explanations

    terms related to oncology and cancer treatment

    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
    ADF
    -0.07
    ahlen
    -0.07
    ë§IJ
    -0.07
    éry
    -0.07
    .Undef
    -0.07
    asic
    -0.07
    ìĶ¨
    -0.07
    æī¿
    -0.07
    eydi
    -0.07
    itimate
    -0.07
    POSITIVE LOGITS
    ive
    0.07
    erset
    0.06
    ç´ł
    0.06
     behalf
    0.06
    ogenic
    0.06
    obox
    0.06
     Suff
    0.06
     Mast
    0.06
     ne
    0.06
    Ú©Ùĩ
    0.06
    Activations Density 0.001%

    No Known Activations