© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 128163
    Prev
    Next
    INDEX
    Explanations

    terms that indicate a high level of complexity or quality in various 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
    que
    -0.07
    kü
    -0.06
    ppy
    -0.06
    ql
    -0.06
    /write
    -0.06
    Ìģt
    -0.06
    uran
    -0.06
     Hur
    -0.06
    azar
    -0.06
    ÑģÑĭ
    -0.06
    POSITIVE LOGITS
    -level
    0.09
    /high
    0.09
    /mod
    0.08
    /exp
    0.08
    /original
    0.08
    -grade
    0.07
     level
    0.07
    utos
    0.07
    ahr
    0.07
    oupon
    0.07
    Activations Density 0.010%

    No Known Activations