© 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. 88270
    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
     Trap
    -0.06
    rint
    -0.06
     OK
    -0.06
     juxtap
    -0.06
     XX
    -0.06
     having
    -0.05
     shoot
    -0.05
     Accept
    -0.05
     Hayward
    -0.05
     skeletal
    -0.05
    POSITIVE LOGITS
    texts
    0.08
    parsers
    0.07
    pace
    0.07
    pecia
    0.07
    Å¡et
    0.07
    ISTER
    0.07
    istani
    0.07
     Baths
    0.07
    èµĸ
    0.07
     texts
    0.07
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.