© 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. 9-LLAMASCOPE-RES-131K
    11. 98367
    Prev
    Next
    INDEX
    Explanations

    terms related to Hindu and Buddhist philosophical concepts and texts

    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
    och
    -0.08
    ius
    -0.07
    £½
    -0.07
    evi
    -0.07
    ampo
    -0.06
     herr
    -0.06
     pref
    -0.06
     precedent
    -0.06
    Prefs
    -0.06
    urgeon
    -0.06
    POSITIVE LOGITS
    itzer
    0.07
    ucken
    0.06
    _FATAL
    0.06
    Subset
    0.06
    _PS
    0.06
    arring
    0.06
     NTN
    0.06
    road
    0.06
     molec
    0.06
    fos
    0.06
    Activations Density 0.008%

    No Known Activations