© 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. 30316
    Prev
    Next
    INDEX
    Explanations

    references to physical locations and descriptions of spaces

    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
    anch
    -0.07
    anka
    -0.07
    aze
    -0.07
    bourg
    -0.07
    dsn
    -0.07
    achuset
    -0.06
    essim
    -0.06
    ystem
    -0.06
    addir
    -0.06
    _instr
    -0.06
    POSITIVE LOGITS
     дÑĢÑĥго
    0.07
    ELY
    0.07
     left
    0.07
     Merry
    0.07
    iek
    0.07
     opposite
    0.06
     others
    0.06
     immediate
    0.06
    itsu
    0.06
     Rak
    0.06
    Activations Density 0.012%

    No Known Activations