© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 9-LLAMASCOPE-RES-131K
    11. 95268
    Prev
    Next
    INDEX
    Explanations

    terminology related to blood clotting and its 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
    etch
    -0.07
    aqu
    -0.07
    hof
    -0.07
    allen
    -0.06
    uple
    -0.06
    dorf
    -0.06
    afort
    -0.06
    uite
    -0.06
    tiles
    -0.06
    isz
    -0.06
    POSITIVE LOGITS
    yna
    0.07
     varsa
    0.07
    AtA
    0.07
    нина
    0.07
    SGlobal
    0.07
     fisse
    0.06
     èĩªåĬ¨çĶŁæĪIJ
    0.06
     synth
    0.06
     tiener
    0.06
    (æľ¨
    0.06
    Activations Density 0.004%

    No Known Activations