© 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. 5-LLAMASCOPE-RES-131K
    11. 125721
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to player signings and contracts in sports

    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
    ssel
    -0.06
    Solo
    -0.06
    andom
    -0.06
    amus
    -0.06
    bows
    -0.06
    879
    -0.06
    mailto
    -0.06
    िध
    -0.06
     Ñħол
    -0.06
    ÙĨدÙĤ
    -0.06
    POSITIVE LOGITS
    _dims
    0.06
    _framework
    0.06
    iya
    0.06
     Wage
    0.06
    kok
    0.06
    êt
    0.06
    wap
    0.06
    onia
    0.06
    .AddListener
    0.06
    JPEG
    0.06
    Activations Density 0.037%

    No Known Activations