© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 78994
    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
    İ
    -0.06
    150
    -0.06
    į°ìĿ´
    -0.06
    jah
    -0.06
    AffineTransform
    -0.06
     Kramer
    -0.06
     information
    -0.06
    ola
    -0.06
    BLOCK
    -0.06
    atile
    -0.05
    POSITIVE LOGITS
    åĴ²
    0.08
    inize
    0.08
    åĦĢ
    0.07
    TRL
    0.07
    _mD
    0.07
    menin
    0.07
    áº
    0.07
    .TryParse
    0.06
    zhou
    0.06
    eless
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.