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

    Neuronpedia

    Jacobian LensNEW
    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. 126577
    Prev
    Next
    INDEX
    Explanations

    phrases related to collaboration and creative works involving multiple people

    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
    raction
    -0.07
     ÑĤÑĢÑĥ
    -0.07
    edio
    -0.07
     гÑĢаж
    -0.07
    egis
    -0.07
    нед
    -0.06
    Trait
    -0.06
    faction
    -0.06
    ulas
    -0.06
    еÑĢо
    -0.06
    POSITIVE LOGITS
     whom
    0.07
    cuts
    0.07
    ırak
    0.06
    اÙĨ
    0.06
     themselves
    0.06
    anson
    0.06
    GRID
    0.06
    ãģ¨ãĤĤ
    0.06
     McCl
    0.06
    amu
    0.06
    Activations Density 0.018%

    No Known Activations