© 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. 27665
    Prev
    Next
    INDEX
    Explanations

    aspects related to spatial concepts and community resources

    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
    ABCDEFGHIJKLMNOP
    -0.07
    á»Ńa
    -0.06
    locker
    -0.06
     hale
    -0.06
     Rect
    -0.06
    552
    -0.06
    anden
    -0.06
    ackets
    -0.06
    ÃŃsto
    -0.06
    HING
    -0.06
    POSITIVE LOGITS
    ér
    0.06
     choice
    0.06
    omencl
    0.06
    stash
    0.06
    straint
    0.06
    éĢģæĸĻçĦ¡æĸĻ
    0.06
    ependency
    0.06
    untu
    0.06
    achen
    0.06
    _tb
    0.06
    Activations Density 0.070%

    No Known Activations