© 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. 88275
    Prev
    Next
    INDEX
    Explanations

    expressions of gratitude and pride within a community or organization

    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
    agal
    -0.08
    PCS
    -0.07
     participating
    -0.07
    ved
    -0.07
    toi
    -0.07
    fak
    -0.06
     án
    -0.06
     Particip
    -0.06
    åıĤåĬł
    -0.06
    PLIED
    -0.06
    POSITIVE LOGITS
     welcoming
    0.07
     him
    0.07
    Welcome
    0.06
    hire
    0.06
     welcomes
    0.06
     welcome
    0.06
     Welcome
    0.06
    hya
    0.06
     hiring
    0.06
    Tabs
    0.06
    Activations Density 0.012%

    No Known Activations