© 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. 120987
    Prev
    Next
    INDEX
    Explanations

    technical terms related to file organization and user data management

    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
     analytic
    -0.07
    embedded
    -0.06
     Zus
    -0.06
    HeaderCode
    -0.06
    sher
    -0.06
    anz
    -0.06
    -gap
    -0.06
    emark
    -0.06
     stray
    -0.06
     sublist
    -0.06
    POSITIVE LOGITS
     Pers
    0.07
    _rw
    0.07
     pers
    0.07
    æı®
    0.07
     writable
    0.07
    Backing
    0.07
     Schro
    0.06
    etri
    0.06
    /Documents
    0.06
    .localized
    0.06
    Activations Density 0.008%

    No Known Activations