© 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. 15-LLAMASCOPE-RES-131K
    11. 86958
    Prev
    Next
    INDEX
    Explanations

    concepts and discussions about potential and transformation

    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
    ksen
    -0.07
    agi
    -0.06
     deep
    -0.06
     subs
    -0.06
     deeply
    -0.06
    unsch
    -0.06
    achi
    -0.06
     twin
    -0.05
    deep
    -0.05
    oden
    -0.05
    POSITIVE LOGITS
    ÑĢаÑĩ
    0.08
    лини
    0.07
    eriod
    0.07
    ä¹³
    0.07
    erdale
    0.07
    ochen
    0.07
     bầu
    0.07
    ,class
    0.07
     nh
    0.07
     ê·¸ëŀĺ
    0.07
    Activations Density 0.000%

    No Known Activations