© 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 EvalsExportsAPI 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. 61083
    Prev
    Next
    INDEX
    Explanations

    specific numerical data and statistical information

    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
    ẩu
    -0.07
    ouv
    -0.07
    zelf
    -0.06
    ille
    -0.06
    vrier
    -0.06
    ElementType
    -0.06
    iggs
    -0.06
    бов
    -0.06
    bsolute
    -0.06
    elles
    -0.06
    POSITIVE LOGITS
     various
    0.18
     several
    0.15
     Various
    0.14
    åIJĦ
    0.14
    åIJĦç§į
    0.13
     both
    0.12
     two
    0.12
    两个
    0.12
    åĩłä¸ª
    0.12
    Various
    0.12
    Activations Density 0.336%

    No Known Activations