© 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. 76457
    Prev
    Next
    INDEX
    Explanations

    references to mint 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
    ivors
    -0.07
     Seks
    -0.06
    indsight
    -0.06
    .Ordinal
    -0.06
    ETS
    -0.06
    pper
    -0.06
    cki
    -0.06
    istics
    -0.06
     exp
    -0.06
     Contents
    -0.06
    POSITIVE LOGITS
    y
    0.08
    ¹
    0.07
    ERRUPT
    0.07
    yw
    0.07
    ãĥ§
    0.07
    trap
    0.07
     гоÑģп
    0.07
    uition
    0.07
    ucky
    0.07
    sett
    0.07
    Activations Density 0.003%

    No Known Activations