© 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. 94771
    Prev
    Next
    INDEX
    Explanations

    specific numerical data and references to official document identifiers

    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
    ặn
    -0.07
    æī±
    -0.06
    .opend
    -0.06
    ãi
    -0.06
    obot
    -0.06
    arel
    -0.06
    ÑĨин
    -0.05
    ìĪĺë¡ľ
    -0.05
     al
    -0.05
     rang
    -0.05
    POSITIVE LOGITS
    iÄħ
    0.07
    ounge
    0.07
    fad
    0.07
    _IW
    0.07
    rray
    0.06
    uten
    0.06
     wij
    0.06
    lauf
    0.06
    unma
    0.06
    894
    0.06
    Activations Density 0.013%

    No Known Activations