© 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. 93755
    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
    dech
    -0.09
    uil
    -0.09
    ç¼
    -0.08
    Ỽt
    -0.08
    ikki
    -0.08
    Ñĥки
    -0.08
    qli
    -0.07
    alles
    -0.07
    iji
    -0.07
    usu
    -0.07
    POSITIVE LOGITS
     Below
    0.06
     Lod
    0.05
     Revel
    0.05
    rror
    0.05
    000
    0.05
     Fil
    0.05
    -unstyled
    0.05
     Graham
    0.05
     greenhouse
    0.05
     DJs
    0.05
    Activations Density 0.003%

    No Known Activations