© 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. 54990
    Prev
    Next
    INDEX
    Explanations

    specific types of technologies or innovation trends

    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
    Ī¬
    -0.08
    ï¸
    -0.07
    Ñĥг
    -0.06
    yne
    -0.06
    gd
    -0.06
    ager
    -0.06
     Cair
    -0.06
    ye
    -0.06
    arter
    -0.06
     dump
    -0.06
    POSITIVE LOGITS
    undry
    0.08
    urm
    0.08
    bstract
    0.08
    locator
    0.08
    undo
    0.07
     BITTE
    0.07
     Tal
    0.07
    Č↵
    0.07
    utterstock
    0.07
    ependency
    0.07
    Activations Density 0.043%

    No Known Activations