© 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. 31030
    Prev
    Next
    INDEX
    Explanations

    elements related to hieroglyphic writing 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
     verbs
    -0.06
    /access
    -0.06
    iker
    -0.06
    keyword
    -0.06
     Au
    -0.06
    erra
    -0.06
    porte
    -0.06
    .Aggressive
    -0.06
     verb
    -0.06
    .Seek
    -0.06
    POSITIVE LOGITS
     unread
    0.08
     writing
    0.08
     characters
    0.07
     пиÑģÑĮмен
    0.07
    опиÑģ
    0.07
    ASURE
    0.07
    kte
    0.07
    ัà¸ģษ
    0.07
    rophy
    0.07
     stroke
    0.07
    Activations Density 0.088%

    No Known Activations