© 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 EvalsExportsAPI 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. 88539
    Prev
    Next
    INDEX
    Explanations

    elements related to music performance and community engagement

    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
     feas
    -0.07
    éľį
    -0.06
     jelly
    -0.06
     Vulner
    -0.06
    723
    -0.06
    emma
    -0.06
     Mov
    -0.06
    çĶ
    -0.05
    ä»
    -0.05
     NavParams
    -0.05
    POSITIVE LOGITS
    ivet
    0.07
    illaume
    0.07
    inton
    0.07
    Å¡em
    0.07
    alez
    0.07
    oland
    0.07
     Prosper
    0.07
    ItemCount
    0.07
    olith
    0.06
    ffen
    0.06
    Activations Density 0.016%

    No Known Activations