© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 31
    Prev
    Next
    INDEX
    Explanations

    references to modern scientific advancements and their implications

    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
     initially
    -0.06
    annah
    -0.06
    acerb
    -0.06
     btw
    -0.06
     tet
    -0.06
     continu
    -0.06
     resultMap
    -0.06
    lá
    -0.06
    ulan
    -0.06
     initial
    -0.06
    POSITIVE LOGITS
    assel
    0.08
     naopak
    0.08
    Pel
    0.07
    inç
    0.07
    .physics
    0.07
     Exceptions
    0.07
    -BEGIN
    0.07
    YLE
    0.07
    (IL
    0.07
     exceptions
    0.07
    Activations Density 0.029%

    No Known Activations