© 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 EvalsExportsAPI 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. 76126
    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
     Haut
    -0.08
    akra
    -0.07
    exus
    -0.07
    γÏĩ
    -0.06
    ystick
    -0.06
     events
    -0.06
    eldom
    -0.06
    ozÃŃ
    -0.06
    pret
    -0.06
    cea
    -0.06
    POSITIVE LOGITS
    à¹ģà¸ģ
    0.07
    abcdefghijklmnop
    0.07
     correl
    0.07
    ÙĨس
    0.07
    mî
    0.07
    TestingModule
    0.06
    .baomidou
    0.06
     ÙħÙĤاÙħ
    0.06
    ABCDEFGHIJKLMNOP
    0.06
    bris
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.