© 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. 41367
    Prev
    Next
    INDEX
    Explanations

    the presence of the abbreviation "Sv" in various contexts

    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
    rella
    -0.09
    onde
    -0.07
     addCriterion
    -0.07
    ei
    -0.07
    iem
    -0.07
    ekim
    -0.07
    isu
    -0.07
    OCUS
    -0.07
    iek
    -0.07
    oes
    -0.07
    POSITIVE LOGITS
     sw
    0.06
    rtype
    0.06
     land
    0.06
     Tr
    0.06
     Nad
    0.06
    arta
    0.06
    ART
    0.06
    ProgressHUD
    0.06
    artz
    0.05
    vas
    0.05
    Activations Density 0.017%

    No Known Activations