© 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. 80030
    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
     through
    -0.06
    through
    -0.06
    ewe
    -0.06
    821
    -0.06
    awk
    -0.06
     zk
    -0.06
    umpt
    -0.06
    ÙĨÙħ
    -0.06
    ewire
    -0.06
    umar
    -0.06
    POSITIVE LOGITS
    _hierarchy
    0.07
    olithic
    0.07
    andi
    0.07
    ripple
    0.07
    íĥķ
    0.06
    .effects
    0.06
    mium
    0.06
    Conv
    0.06
    _invoke
    0.06
    اذ
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.