© 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 EvalsExportsAPI 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. 93896
    Prev
    Next
    INDEX
    Explanations

    references to medical professionals or related abbreviations

    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
    reib
    -0.08
    Multiply
    -0.07
    rades
    -0.07
    lingen
    -0.07
    ceae
    -0.06
    pers
    -0.06
    ÅĻik
    -0.06
    ABL
    -0.06
    ceive
    -0.06
    indow
    -0.06
    POSITIVE LOGITS
     sát
    0.07
     ê°ĸ
    0.06
    uncio
    0.06
     Cata
    0.06
    oco
    0.06
    oser
    0.06
    Unc
    0.06
     Grass
    0.05
    ann
    0.05
     Rear
    0.05
    Activations Density 0.041%

    No Known Activations