© 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. 18291
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     void
    -0.07
    åıĬ
    -0.06
    oran
    -0.06
     Shuffle
    -0.06
    âĢħ
    -0.06
    CTest
    -0.06
     poly
    -0.06
    phabet
    -0.05
    agrams
    -0.05
    cade
    -0.05
    POSITIVE LOGITS
     TCHAR
    0.07
    ãĤıãģij
    0.07
     CharSequence
    0.07
    ://%
    0.07
    reative
    0.07
     RedirectTo
    0.07
    gem
    0.06
    оÑģÑĤи
    0.06
    gesi
    0.06
    _PAD
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.