© 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. 119650
    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
    hurst
    -0.07
     Schul
    -0.06
    uzzi
    -0.06
    ä
    -0.06
    onn
    -0.06
    ÑģÑİ
    -0.06
     Shak
    -0.06
     Zo
    -0.06
    bias
    -0.06
     ch
    -0.06
    POSITIVE LOGITS
    Ñĺ
    0.08
    oriented
    0.07
    izr
    0.07
    ilate
    0.07
     Mate
    0.07
    çĻ»åł´
    0.07
    ä¼¼çļĦ
    0.07
    rowned
    0.07
     Äij
    0.07
    dialogs
    0.07
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.