© 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. 119936
    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
    ικη
    -0.08
    mamak
    -0.08
    âĢ¦"↵↵
    -0.08
    ·¸
    -0.08
    okt
    -0.07
    lide
    -0.07
    Gatt
    -0.07
    LLU
    -0.07
     springfox
    -0.07
    inness
    -0.07
    POSITIVE LOGITS
    m
    0.06
    up
    0.06
    0.06
    u
    0.06
     involving
    0.06
     Elk
    0.05
     fascination
    0.05
    atro
    0.05
    202
    0.05
     dealing
    0.05
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.