© 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. 107538
    Prev
    Next
    INDEX
    Explanations

    references to divine creation and authority

    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
    ducers
    -0.06
    ÙĤر
    -0.06
    ORIZED
    -0.06
    cord
    -0.06
     Stones
    -0.06
    жив
    -0.06
    _aliases
    -0.06
    ãģijãĤĮãģ©
    -0.06
    ικ
    -0.06
    routeParams
    -0.06
    POSITIVE LOGITS
    _asc
    0.07
     myself
    0.07
    UPI
    0.07
     Kl
    0.06
    oine
    0.06
     Sabb
    0.06
    oon
    0.06
    plex
    0.06
    kl
    0.06
    Detach
    0.06
    Activations Density 0.006%

    No Known Activations