© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 93630
    Prev
    Next
    INDEX
    Explanations

    phrases related to content usage rights and permissions

    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
    urum
    -0.07
    onom
    -0.07
    lement
    -0.07
    лиÑĪком
    -0.07
    isse
    -0.06
    gard
    -0.06
    larg
    -0.06
     eldre
    -0.06
    IMA
    -0.06
    ensem
    -0.06
    POSITIVE LOGITS
    æľīéĻIJ
    0.07
     limited
    0.07
    許
    0.06
     permission
    0.06
    Limited
    0.06
    æĿĥéĻIJ
    0.06
    czas
    0.06
    uil
    0.06
     resid
    0.06
    temporary
    0.06
    Activations Density 0.003%

    No Known Activations