© 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. 75059
    Prev
    Next
    INDEX
    Explanations

    references to saving documents or files

    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
    ↵
    -0.06
    ureka
    -0.06
    -
    -0.06
     Correspond
    -0.06
     Consent
    -0.06
    uso
    -0.06
    -le
    -0.06
    yll
    -0.06
    ilt
    -0.06
    acy
    -0.06
    POSITIVE LOGITS
    (save
    0.09
    OrUpdate
    0.08
    ToFile
    0.08
    .sav
    0.08
    .Save
    0.08
    ToDevice
    0.08
     onSave
    0.07
    /loading
    0.07
     Saves
    0.07
    InstanceState
    0.07
    Activations Density 0.013%

    No Known Activations