© 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. 61493
    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
    exemple
    -0.07
    atu
    -0.06
    omit
    -0.06
    acic
    -0.06
     Penn
    -0.06
    addon
    -0.06
    reon
    -0.05
     district
    -0.05
     figures
    -0.05
    ][]
    -0.05
    POSITIVE LOGITS
    technology
    0.07
    ukan
    0.07
    ural
    0.07
     technolog
    0.07
    IVATE
    0.07
     Keeper
    0.07
    Technology
    0.07
    สำ
    0.07
     Technology
    0.07
     näch
    0.07
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.