© 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. 9-LLAMASCOPE-RES-131K
    11. 96348
    Prev
    Next
    INDEX
    Explanations

    names of notable individuals in sports or entertainment

    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
    unar
    -0.09
     dán
    -0.08
    idor
    -0.08
    룡
    -0.07
    ona
    -0.07
    eks
    -0.07
    osto
    -0.07
    rait
    -0.07
    ONA
    -0.07
    ÎķÎļ
    -0.07
    POSITIVE LOGITS
    uales
    0.06
    jer
    0.06
    355
    0.05
     Schwarz
    0.05
    606
    0.05
    ahan
    0.05
     Electric
    0.05
     Schwe
    0.05
     ler
    0.05
     family
    0.05
    Activations Density 0.001%

    No Known Activations