© 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 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. 17-LLAMASCOPE-RES-131K
    11. 78343
    Prev
    Next
    INDEX
    Explanations

    terms related to pilgrimage and the act of traveling for spiritual purposes

    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
    AKE
    -0.07
    ities
    -0.07
    manship
    -0.07
    cheng
    -0.07
    elligence
    -0.07
    ernity
    -0.06
    ITIES
    -0.06
    eled
    -0.06
    rud
    -0.06
    ake
    -0.06
    POSITIVE LOGITS
    urally
    0.07
    475
    0.07
     вог
    0.07
    ogue
    0.07
    uard
    0.07
    iband
    0.07
    oftware
    0.07
    feld
    0.07
    XP
    0.06
     trip
    0.06
    Activations Density 0.002%

    No Known Activations