© 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. 93860
    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
    اÙĬØ´
    -0.06
    Touches
    -0.06
     McCart
    -0.06
    erti
    -0.06
    getOption
    -0.06
    ni
    -0.06
     Caucus
    -0.06
    netinet
    -0.06
     gezocht
    -0.06
     СовеÑĤ
    -0.06
    POSITIVE LOGITS
    ãģ²ãģ¨
    0.07
     kalk
    0.07
    beg
    0.07
    odus
    0.06
    Ãłm
    0.06
    udden
    0.06
    ģm
    0.06
    conde
    0.06
    ideo
    0.06
    chter
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.