© 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. 127671
    Prev
    Next
    INDEX
    Explanations

    references to rights and legal entitlements

    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
    elastic
    -0.07
    au
    -0.06
    egen
    -0.06
     <!--[
    -0.06
    -p
    -0.06
    935
    -0.06
    eln
    -0.06
    LT
    -0.06
    om
    -0.06
     prem
    -0.06
    POSITIVE LOGITS
     rights
    0.17
     RIGHTS
    0.15
     Rights
    0.14
    rights
    0.14
    Rights
    0.13
    -rights
    0.12
     entitled
    0.11
    _rights
    0.10
     entitlement
    0.10
     пÑĢава
    0.10
    Activations Density 0.033%

    No Known Activations