© 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 EvalsExportsAPI 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. 106595
    Prev
    Next
    INDEX
    Explanations

    references to locations and settings related to waste disposal

    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
    ardon
    -0.09
    arov
    -0.08
    оба
    -0.08
    gii
    -0.08
    olini
    -0.08
    amedi
    -0.07
    oload
    -0.07
    ologne
    -0.07
    úb
    -0.07
    iddi
    -0.07
    POSITIVE LOGITS
     externally
    0.06
     Dahl
    0.06
     Caldwell
    0.06
     or
    0.05
    ven
    0.05
    st
    0.05
    Fo
    0.05
    nis
    0.05
    755
    0.05
    327
    0.05
    Activations Density 0.003%

    No Known Activations