© 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. 30140
    Prev
    Next
    INDEX
    Explanations

    references to financial statements and reports

    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
    Ñıж
    -0.07
     simul
    -0.07
    _cores
    -0.06
    otron
    -0.06
    ëħ
    -0.06
    gın
    -0.06
    .getIn
    -0.06
    rego
    -0.06
    grass
    -0.06
    .ServiceModel
    -0.06
    POSITIVE LOGITS
    /report
    0.07
    ElementException
    0.06
    idente
    0.06
    iske
    0.06
     defaultManager
    0.06
    swers
    0.06
     offseason
    0.06
    iesel
    0.06
     Bookmark
    0.06
    èĬ
    0.06
    Activations Density 0.001%

    No Known Activations