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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 126434
    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
     дÑĸ
    -0.07
    ystore
    -0.07
    egt
    -0.06
    arp
    -0.06
    aminer
    -0.06
    :convert
    -0.06
    ags
    -0.06
     Gibson
    -0.06
    ISP
    -0.06
    Adapter
    -0.06
    POSITIVE LOGITS
    enen
    0.08
     parity
    0.07
    ινÏĮ
    0.07
    ãģ£ãģ¡
    0.07
    ende
    0.07
    ylan
    0.06
    çĿ
    0.06
    quoi
    0.06
     programming
    0.06
     Programming
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.