© 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. 30755
    Prev
    Next
    INDEX
    Explanations

    specific patterns related to time, organization, and numerical data

    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
    achs
    -0.08
    ses
    -0.07
    /from
    -0.07
    radient
    -0.07
    /to
    -0.07
    alus
    -0.07
    ebo
    -0.06
    /small
    -0.06
    Æ°á»Ľc
    -0.06
     Campos
    -0.06
    POSITIVE LOGITS
     addCriterion
    0.07
    ché
    0.07
    362
    0.07
    493
    0.06
    905
    0.06
    itä
    0.06
    åĿĢ
    0.06
    ÃĦ
    0.06
    Jvm
    0.06
    -valu
    0.06
    Activations Density 0.052%

    No Known Activations