© 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. 17-LLAMASCOPE-RES-131K
    11. 18175
    Prev
    Next
    INDEX
    Explanations

    references to spiritual or philosophical concepts

    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
    arend
    -0.06
    arf
    -0.06
     ÐŁÐ¾Ñĩ
    -0.06
    imes
    -0.06
     cach
    -0.06
     Civil
    -0.06
    iles
    -0.06
    igm
    -0.05
    ACS
    -0.05
    ãĥ¼ãĥĸãĥ«
    -0.05
    POSITIVE LOGITS
    zyst
    0.08
    leanup
    0.07
     fitte
    0.07
    _closure
    0.07
    bum
    0.07
    ectl
    0.07
     voks
    0.07
    дап
    0.06
    doch
    0.06
     buflen
    0.06
    Activations Density 0.011%

    No Known Activations