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

    Neuronpedia

    Jacobian LensNEW
    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. 17-LLAMASCOPE-RES-131K
    11. 59044
    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
    ynchronously
    -0.07
    uniform
    -0.07
    .parsers
    -0.07
     lifted
    -0.06
     tiles
    -0.06
    rgan
    -0.06
    éĢ£
    -0.06
     mote
    -0.06
    borough
    -0.06
     lift
    -0.06
    POSITIVE LOGITS
    ifax
    0.07
    æĹıèĩªæ²»
    0.07
    Tip
    0.06
     unl
    0.06
    ụy
    0.06
     Contents
    0.06
    ghost
    0.06
     Bag
    0.06
     Feinstein
    0.06
     Tip
    0.06
    Activations Density 0.003%

    No Known Activations