© 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. 70515
    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
    DRV
    -0.07
    RefCount
    -0.07
    sono
    -0.07
     æ·
    -0.07
    athlon
    -0.07
     Tamil
    -0.07
     tamil
    -0.07
     नर
    -0.07
    łí
    -0.06
     Narendra
    -0.06
    POSITIVE LOGITS
     Egypt
    0.17
     Egyptian
    0.17
     Cairo
    0.16
    Egypt
    0.16
     Nile
    0.15
     Egyptians
    0.15
     Ùħصر
    0.12
     cairo
    0.12
    gypt
    0.11
     Kansas
    0.10
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.