© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 121543
    Prev
    Next
    INDEX
    Explanations

    the variations and occurrences of the name "Ram" in different contexts

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    ift
    -0.07
    osis
    -0.07
    a
    -0.07
    icari
    -0.06
    PLE
    -0.06
    surface
    -0.06
    ioso
    -0.06
    MDB
    -0.06
    imens
    -0.06
    >:</
    -0.06
    POSITIVE LOGITS
    irez
    0.09
    Å¡ak
    0.08
    mps
    0.07
    inder
    0.07
    allo
    0.07
    alama
    0.07
     Rams
    0.07
    ť
    0.06
    shade
    0.06
    INDER
    0.06
    Activations Density 0.008%

    No Known Activations