© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-131K
    6. 90370
    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
    leigh
    -0.07
     assort
    -0.06
    .byId
    -0.06
    mainwindow
    -0.06
    AIT
    -0.06
     ÙĪØ§Ø¨
    -0.06
     famil
    -0.06
    if
    -0.05
    isse
    -0.05
    akk
    -0.05
    POSITIVE LOGITS
    afone
    0.08
     urban
    0.07
    ocity
    0.07
    ูà¸Ĺ
    0.07
    ngine
    0.07
    ágina
    0.07
    elmet
    0.07
     Planner
    0.07
    inki
    0.07
    design
    0.07
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.