© 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. 14561
    Prev
    Next
    INDEX
    Explanations

    numbers or numeric values in a text

    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
    raphics
    -0.07
    guard
    -0.07
    erli
    -0.07
    Ø´ÙĪر
    -0.06
    CAL
    -0.06
    izador
    -0.06
    lıģına
    -0.06
    nection
    -0.06
    OCR
    -0.06
    меÑĩ
    -0.06
    POSITIVE LOGITS
    âĢ³
    0.10
    ï¸ı
    0.08
    âĢ²
    0.08
    ipeg
    0.06
    rd
    0.06
    ì§ľ
    0.06
    th
    0.06
     عشر
    0.06
     of
    0.06
    teenth
    0.06
    Activations Density 0.050%

    No Known Activations