© 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. 125146
    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
    ãĤ
    -0.06
     Aren
    -0.06
     å¯
    -0.06
    -esque
    -0.06
     Progressive
    -0.06
     Mah
    -0.06
    ugi
    -0.06
     âŁ
    -0.06
     mant
    -0.06
    uss
    -0.05
    POSITIVE LOGITS
    iverz
    0.07
     harc
    0.07
    oft
    0.07
    cad
    0.07
    ανδ
    0.07
     Bilim
    0.07
     ÑĢаб
    0.06
    ModelIndex
    0.06
    >manual
    0.06
     Böl
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.