© 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. 28648
    Prev
    Next
    INDEX
    Explanations

    references to compensation or payment

    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
    zeigen
    -0.07
    oss
    -0.07
    egra
    -0.07
    PropTypes
    -0.07
    exampleModal
    -0.07
    人çī©
    -0.06
    ÑĪки
    -0.06
    ecta
    -0.06
    ethe
    -0.06
    Bindings
    -0.06
    POSITIVE LOGITS
    ilik
    0.07
    ronic
    0.06
    ymoon
    0.06
     p
    0.06
    mium
    0.06
     visit
    0.06
     IonicModule
    0.06
    olumn
    0.06
    ARENT
    0.05
    /lic
    0.05
    Activations Density 0.005%

    No Known Activations