© 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. 15085
    Prev
    Next
    INDEX
    Explanations

    technical terms related to arrays and coordinates in a spatial system

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    ucid
    -0.08
    mue
    -0.07
    ERG
    -0.07
    寸
    -0.07
     Vys
    -0.07
    ounds
    -0.07
    ãģıãģł
    -0.07
    anje
    -0.07
    arra
    -0.07
    inch
    -0.07
    POSITIVE LOGITS
     direction
    0.22
     directions
    0.19
     Direction
    0.18
    direction
    0.17
     Directions
    0.17
    æĸ¹åIJij
    0.17
    Direction
    0.15
    _direction
    0.14
    -direction
    0.14
     dirección
    0.14
    Activations Density 0.214%

    No Known Activations