Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 22-LLAMASCOPE-RES-131K
    6. 5500
    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
     gar
    -0.07
     Serif
    -0.07
    olley
    -0.07
    akat
    -0.07
    anches
    -0.07
    _FATAL
    -0.07
    ä¹³
    -0.07
    .gdx
    -0.07
    -window
    -0.06
    ERP
    -0.06
    POSITIVE LOGITS
     Switch
    0.09
    .opendaylight
    0.09
     network
    0.08
     Programm
    0.08
     Packet
    0.08
     switches
    0.08
     programm
    0.08
     switching
    0.08
     packet
    0.08
    network
    0.08
    Activations Density 0.039%

    No Known Activations