© 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. 116945
    Prev
    Next
    INDEX
    Explanations

    terms related to safety and maintenance checks

    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
    RLF
    -0.06
    literal
    -0.06
    redo
    -0.06
    vala
    -0.06
    ple
    -0.06
    urma
    -0.06
    arro
    -0.06
    ingo
    -0.06
    ober
    -0.06
    umpy
    -0.06
    POSITIVE LOGITS
     Nes
    0.07
     Klo
    0.06
     functioning
    0.06
     condition
    0.06
    zar
    0.06
     Tes
    0.06
    اÙĦت
    0.06
    (Api
    0.06
     sol
    0.06
    .navigator
    0.06
    Activations Density 0.004%

    No Known Activations