© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 107031
    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
    PMC
    -0.06
    othy
    -0.06
    uche
    -0.06
     comfort
    -0.06
    εÏģι
    -0.06
     Ster
    -0.06
     shopping
    -0.06
    mall
    -0.06
     Kaynak
    -0.05
    å°ļ
    -0.05
    POSITIVE LOGITS
    826
    0.07
     maybe
    0.07
    574
    0.07
    à¸ļà¸Ħ
    0.07
    .liferay
    0.06
    áºŃn
    0.06
    .mutex
    0.06
    plevel
    0.06
    GetObject
    0.06
     helicopt
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.