© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 15-LLAMASCOPE-RES-131K
    11. 88897
    Prev
    Next
    INDEX
    Explanations

    references to service providers in the context of waste management

    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
    óc
    -0.06
     nose
    -0.06
    acers
    -0.06
    ubi
    -0.06
    604
    -0.06
    oplay
    -0.06
    OB
    -0.05
    oui
    -0.05
    ahkan
    -0.05
    hog
    -0.05
    POSITIVE LOGITS
     addCriterion
    0.07
    471
    0.07
    avery
    0.07
    alcon
    0.07
    ippo
    0.06
    arend
    0.06
     Dover
    0.06
     Deniz
    0.06
    alon
    0.06
    gnore
    0.06
    Activations Density 0.001%

    No Known Activations