© 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. 15-LLAMASCOPE-RES-131K
    11. 86814
    Prev
    Next
    INDEX
    Explanations

    programming commands or operations related to setting values in a structure

    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
    odies
    -0.07
    arb
    -0.06
    etch
    -0.06
    evi
    -0.06
    ellar
    -0.06
     clin
    -0.06
    rens
    -0.05
    æ¬
    -0.05
     semp
    -0.05
     birth
    -0.05
    POSITIVE LOGITS
    chal
    0.07
    dorf
    0.07
    Unchecked
    0.07
    ovit
    0.07
    alloca
    0.07
    ourcem
    0.07
    ÑĨез
    0.07
     ********************************************************
    0.06
    IFY
    0.06
    nim
    0.06
    Activations Density 0.024%

    No Known Activations