© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-131K
    6. 89037
    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
    INTR
    -0.07
    741
    -0.07
     Creek
    -0.06
     Sand
    -0.06
     SAND
    -0.06
    artz
    -0.06
    742
    -0.06
     Dimensions
    -0.06
    Sand
    -0.06
    .Ma
    -0.06
    POSITIVE LOGITS
    ãĥ¼ãĥį
    0.07
    ennent
    0.07
    ONUS
    0.07
    gli
    0.07
    ariant
    0.07
    VERR
    0.07
     onDataChange
    0.06
    SharedPointer
    0.06
    ierz
    0.06
     escorte
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.