© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 89531
    Prev
    Next
    INDEX
    Explanations

    words related to spatial relationships and directions

    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
    844
    -0.09
    VEC
    -0.06
    olson
    -0.06
     minimum
    -0.06
    обов
    -0.06
    syntax
    -0.06
    à¸Ŀ
    -0.05
    abile
    -0.05
    رÙģ
    -0.05
     Rus
    -0.05
    POSITIVE LOGITS
    tres
    0.08
    ови
    0.07
     ï½ľ
    0.07
    wares
    0.07
    hiba
    0.07
     огÑĢа
    0.07
    ware
    0.07
    ostat
    0.07
    pez
    0.07
    lopen
    0.07
    Activations Density 0.205%

    No Known Activations