© 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 EvalsExportsinterp-engineNEWAPI 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. 2130
    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
    asco
    -0.07
    borg
    -0.06
     برابر
    -0.06
    iskey
    -0.06
    atif
    -0.06
    ateurs
    -0.06
    -setup
    -0.06
    aroo
    -0.06
     Ùħد
    -0.06
     çoÄŁ
    -0.06
    POSITIVE LOGITS
     nearby
    0.29
     neighboring
    0.22
     neighbouring
    0.20
     adjacent
    0.19
     ÑģоÑģед
    0.16
     Nearby
    0.15
    éĻĦè¿ij
    0.14
     neighbor
    0.14
     adjoining
    0.13
     neighbour
    0.13
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.