© 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. 9-LLAMASCOPE-RES-131K
    11. 97415
    Prev
    Next
    INDEX
    Explanations

    phrases or terms related to measurements and distributions

    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
    oland
    -0.06
    ulia
    -0.06
    iol
    -0.06
    uras
    -0.06
     Licht
    -0.06
     Ung
    -0.06
    amientos
    -0.06
    quina
    -0.06
     how
    -0.06
    atsby
    -0.06
    POSITIVE LOGITS
    ãĥ³ãĥĪ
    0.08
    isay
    0.07
    ugu
    0.07
    enville
    0.07
    à¥Ĥद
    0.06
     Hubbard
    0.06
    зÑĥ
    0.06
    .layoutControl
    0.06
    _SDK
    0.06
    appen
    0.06
    Activations Density 0.001%

    No Known Activations