© 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. 62725
    Prev
    Next
    INDEX
    Explanations

    terms related to documentation and collections

    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
    ollen
    -0.07
    DataContext
    -0.07
    dek
    -0.07
    ãĥ©ãĤ¤ãĥ³
    -0.07
    .yy
    -0.06
    ейÑģÑĤв
    -0.06
     Chess
    -0.06
    /devices
    -0.06
    GINE
    -0.06
    .CG
    -0.06
    POSITIVE LOGITS
    pedia
    0.07
    )prepare
    0.07
    ulk
    0.06
    èĹ
    0.06
    swick
    0.06
    RD
    0.06
    mtree
    0.06
    lang
    0.06
    rit
    0.06
    odi
    0.06
    Activations Density 0.005%

    No Known Activations