© 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. 17-LLAMASCOPE-RES-131K
    11. 127118
    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
    ائب
    -0.07
    STDOUT
    -0.07
     unint
    -0.07
    _pitch
    -0.07
    окон
    -0.07
    LLU
    -0.06
    980
    -0.06
    ienie
    -0.06
     Picker
    -0.06
    =$('#
    -0.06
    POSITIVE LOGITS
    uta
    0.07
    .gdx
    0.07
     Advis
    0.06
     tomorrow
    0.06
     operative
    0.06
    ashi
    0.06
    Conv
    0.06
    adows
    0.06
     normals
    0.06
    ipping
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.