© 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. 30284
    Prev
    Next
    INDEX
    Explanations

    phrases indicating contributions or offerings made by individuals or organizations

    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
    ioned
    -0.07
    elib
    -0.07
    ĨĴ
    -0.06
    zeitig
    -0.06
    amber
    -0.06
    ités
    -0.06
    ambio
    -0.06
    usk
    -0.06
    idos
    -0.06
    ÅĤem
    -0.06
    POSITIVE LOGITS
     table
    0.09
     bear
    0.08
    bear
    0.07
    olis
    0.07
     equation
    0.07
    table
    0.07
     discussions
    0.06
    veau
    0.06
    Bear
    0.06
    Dyn
    0.06
    Activations Density 0.012%

    No Known Activations