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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 29002
    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
    .sg
    -0.06
    éĻ·
    -0.06
    Łèĥ½
    -0.06
    resenter
    -0.06
    ilder
    -0.06
     Conserv
    -0.06
     surround
    -0.06
     اÙĦÙħر
    -0.06
    027
    -0.06
    _Buffer
    -0.06
    POSITIVE LOGITS
    upertino
    0.07
     sez
    0.06
    ÙĥÙĪ
    0.06
    hausen
    0.06
    nite
    0.06
     ApplicationException
    0.06
    IODevice
    0.06
    ithe
    0.06
     Civic
    0.06
     hur
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.