© 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. 17-LLAMASCOPE-RES-131K
    11. 106526
    Prev
    Next
    INDEX
    Explanations

    elements related to analysis and evaluation of models or systems

    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
    isan
    -0.08
    ÙĦÙħÙĩ
    -0.07
    adden
    -0.06
    íĥķ
    -0.06
    auen
    -0.06
    iphy
    -0.06
    /Index
    -0.06
     Coff
    -0.06
    iare
    -0.06
    kir
    -0.06
    POSITIVE LOGITS
    asti
    0.07
    ftar
    0.07
    ırı
    0.06
    eti
    0.06
     Crew
    0.06
    bserv
    0.06
    IRTH
    0.06
    uto
    0.06
    ograd
    0.06
    CTOR
    0.06
    Activations Density 0.037%

    No Known Activations