© 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. 14486
    Prev
    Next
    INDEX
    Explanations

    terms related to data and analytics

    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
    nement
    -0.08
    nie
    -0.08
    è¾ij
    -0.07
    üstü
    -0.07
    specs
    -0.07
    kü
    -0.07
    NING
    -0.07
    ings
    -0.07
    picker
    -0.07
     multiplic
    -0.07
    POSITIVE LOGITS
     Morm
    0.08
    ALLY
    0.07
    -enabled
    0.07
    bles
    0.06
    iasi
    0.06
    /debug
    0.06
    aden
    0.06
    TXT
    0.06
    ê¹
    0.06
    eum
    0.06
    Activations Density 0.003%

    No Known Activations