© 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. 18815
    Prev
    Next
    INDEX
    Explanations

    terms related to "Elasticsearch" and its components in code 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
    isl
    -0.06
    stad
    -0.06
    iface
    -0.06
    _parents
    -0.06
    NESS
    -0.06
    .Networking
    -0.06
    olls
    -0.06
    hey
    -0.05
    ľ
    -0.05
    cken
    -0.05
    POSITIVE LOGITS
    tout
    0.07
    meni
    0.07
    oft
    0.07
    fleet
    0.07
    vla
    0.06
    zung
    0.06
    ãĤ¨ãĥ«
    0.06
    áng
    0.06
    alim
    0.06
    enance
    0.06
    Activations Density 0.009%

    No Known Activations