© 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. 55604
    Prev
    Next
    INDEX
    Explanations

    recurring phrases related to terms, conditions, and agreements

    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
    wind
    -0.07
    feld
    -0.07
    miÅŁ
    -0.06
     intake
    -0.06
    939
    -0.06
    mir
    -0.06
    882
    -0.06
    ue
    -0.06
    327
    -0.06
    mont
    -0.06
    POSITIVE LOGITS
    erif
    0.07
    andles
    0.07
    ASIC
    0.07
    olio
    0.06
     resc
    0.06
    amma
    0.06
     Viol
    0.06
    ropol
    0.06
    gow
    0.06
    onitor
    0.06
    Activations Density 0.002%

    No Known Activations