© 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. 124406
    Prev
    Next
    INDEX
    Explanations

    biographical details about authors

    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
    favor
    -0.08
     Colbert
    -0.07
    okol
    -0.07
     favored
    -0.07
     Favor
    -0.07
    ansa
    -0.07
    RTL
    -0.07
    amburg
    -0.07
     Tome
    -0.06
    大åħ¨
    -0.06
    POSITIVE LOGITS
     Oxford
    0.07
     Pound
    0.07
     Mandal
    0.07
    ãĥ¼ãĤ¹ãĥĪ
    0.06
     Tolkien
    0.06
    .cam
    0.06
    åĿª
    0.06
    tees
    0.06
     bicy
    0.06
    Lord
    0.06
    Activations Density 0.034%

    No Known Activations