© 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. 4513
    Prev
    Next
    INDEX
    Explanations

    references to warriors and spiritual concepts in a religious context

    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
     Torch
    -0.07
    awah
    -0.06
    Experiment
    -0.06
    ahat
    -0.06
    ackbar
    -0.06
    енз
    -0.06
     Moff
    -0.06
    ContentPane
    -0.06
    andler
    -0.06
    rint
    -0.06
    POSITIVE LOGITS
     erotische
    0.08
     Pand
    0.06
     famously
    0.06
    fone
    0.06
     Microsystems
    0.06
    èĨ
    0.06
    _usec
    0.06
    اÙĦÙĬا
    0.06
    èĮ¨
    0.06
    rup
    0.06
    Activations Density 0.004%

    No Known Activations