© 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. 84198
    Prev
    Next
    INDEX
    Explanations

    terms related to software programming and data serialization

    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
    orea
    -0.08
    celik
    -0.06
     Kore
    -0.06
    важа
    -0.06
     hrom
    -0.06
     bát
    -0.06
    _Util
    -0.06
    odash
    -0.06
    orado
    -0.06
    rael
    -0.06
    POSITIVE LOGITS
     ObjectOutputStream
    0.09
    pickle
    0.08
     saves
    0.08
     save
    0.08
     serialVersionUID
    0.08
    .sav
    0.07
     pickle
    0.07
     sav
    0.07
     onSave
    0.07
    .pkl
    0.07
    Activations Density 0.033%

    No Known Activations