© 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. 62384
    Prev
    Next
    INDEX
    Explanations

    themes related to collaborative and creative projects, particularly in artistic 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
    èo
    -0.08
    ÑħÑĥ
    -0.07
    Ñĥки
    -0.07
     proh
    -0.07
    uzz
    -0.07
    åIJ§
    -0.07
     telefon
    -0.07
    iego
    -0.07
    .Dependency
    -0.06
    _ul
    -0.06
    POSITIVE LOGITS
    ï¼ĮæīĢ以
    0.23
     therefore
    0.21
    æīĢ以
    0.19
     Therefore
    0.19
     hence
    0.18
     nên
    0.18
    ï¼ĮåĽłæѤ
    0.18
     поÑįÑĤомÑĥ
    0.17
     so
    0.17
    Therefore
    0.17
    Activations Density 1.018%

    No Known Activations