© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 82515
    Prev
    Next
    INDEX
    Explanations

    concepts related to biology and anatomy, particularly focusing on the human body and its systems

    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
    arih
    -0.07
    ahn
    -0.07
    ÑģÑĤÑĥп
    -0.07
     tob
    -0.07
     tot
    -0.07
     kari
    -0.07
    ãĤ«ãĥĨãĤ´ãĥª
    -0.07
    .Serial
    -0.07
    estre
    -0.06
    лада
    -0.06
    POSITIVE LOGITS
     via
    0.11
    via
    0.09
     Via
    0.07
    _via
    0.07
    WARDED
    0.07
    etable
    0.07
    Via
    0.06
     thereby
    0.06
     instead
    0.06
    lparr
    0.06
    Activations Density 0.024%

    No Known Activations