© 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. 82011
    Prev
    Next
    INDEX
    Explanations

    references to collaborative projects and initiatives in education and the arts

    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
     prof
    -0.07
    urve
    -0.06
    ItemSelected
    -0.06
    deck
    -0.06
     assort
    -0.06
    acket
    -0.06
    pra
    -0.06
    าà¸ĩ
    -0.06
     magn
    -0.06
    clearfix
    -0.06
    POSITIVE LOGITS
     project
    0.09
    project
    0.07
     proje
    0.07
    /projects
    0.07
     PARTIC
    0.07
     projectName
    0.06
    irling
    0.06
    -community
    0.06
    (project
    0.06
     workshop
    0.06
    Activations Density 0.102%

    No Known Activations