© 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. 126091
    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
    upert
    -0.06
    jer
    -0.06
     rig
    -0.06
    ì¶ĺ
    -0.06
     needing
    -0.06
     모ì§ij
    -0.06
    ISTORY
    -0.06
     Malk
    -0.06
    ÑĢÑı
    -0.06
    боÑĢа
    -0.05
    POSITIVE LOGITS
     Foreign
    0.07
    _foreign
    0.07
     recep
    0.07
    -host
    0.07
    Foreign
    0.07
     FOREIGN
    0.06
     foreign
    0.06
    ofil
    0.06
    inerary
    0.06
     condol
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.