© 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. 98083
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to Hinduism and its philosophical 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
    xic
    -0.07
    ald
    -0.07
    idon
    -0.06
    bsolute
    -0.06
    eres
    -0.06
    tep
    -0.06
    ssi
    -0.06
    nbsp
    -0.06
    oller
    -0.06
    sale
    -0.06
    POSITIVE LOGITS
     McInt
    0.08
    pson
    0.07
    -Isl
    0.07
    -Muslim
    0.07
    -Christian
    0.07
    że
    0.07
    ized
    0.07
    Å¡ka
    0.06
    -Sah
    0.06
     horns
    0.06
    Activations Density 0.005%

    No Known Activations