© 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. 15-LLAMASCOPE-RES-131K
    11. 89116
    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
    allet
    -0.07
    onga
    -0.07
    alo
    -0.06
     voll
    -0.06
     McInt
    -0.06
    ongo
    -0.05
    aro
    -0.05
    ongyang
    -0.05
    ene
    -0.05
    jal
    -0.05
    POSITIVE LOGITS
    æ°ij
    0.07
    icap
    0.07
    Credits
    0.07
    Äł
    0.07
    ucks
    0.06
    owie
    0.06
    wand
    0.06
    ÏĦÏģα
    0.06
    .setViewport
    0.06
    ãĥªãĥ¼ãĤº
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.