© 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. 17-LLAMASCOPE-RES-131K
    11. 78063
    Prev
    Next
    INDEX
    Explanations

    descriptors related to experiences and emotions in various contexts

    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
     hete
    -0.06
     destinationViewController
    -0.06
     suche
    -0.06
     ub
    -0.06
     provinc
    -0.06
    loff
    -0.06
    _tF
    -0.06
     lazım
    -0.06
     simul
    -0.06
    chalk
    -0.06
    POSITIVE LOGITS
     ones
    0.08
    ness
    0.07
    antiago
    0.07
    pNext
    0.06
    allest
    0.06
    lest
    0.06
    &W
    0.06
    çļĦãģª
    0.06
     stuff
    0.06
    ìłģìĿ¸
    0.06
    Activations Density 0.160%

    No Known Activations