© 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. 117314
    Prev
    Next
    INDEX
    Explanations

    references to music production and collaboration

    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
    üven
    -0.07
    ieee
    -0.07
    elsea
    -0.07
    apiro
    -0.07
    MenuBar
    -0.07
    éné
    -0.07
    USIC
    -0.07
    beiter
    -0.07
    ainen
    -0.07
    emoth
    -0.07
    POSITIVE LOGITS
    axe
    0.06
    ingles
    0.06
     hit
    0.06
     Believe
    0.06
     Reload
    0.06
    rex
    0.05
     cle
    0.05
     Stamina
    0.05
     singles
    0.05
    Hits
    0.05
    Activations Density 0.000%

    No Known Activations