© 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 EvalsExportsinterp-engineNEWAPI 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. 39186
    Prev
    Next
    INDEX
    Explanations

    references to selling or commerce-related activities

    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
     Nem
    -0.06
     Gil
    -0.06
    ula
    -0.06
    hire
    -0.05
     deposit
    -0.05
     discussion
    -0.05
     ta
    -0.05
     stage
    -0.05
     guard
    -0.05
    ligt
    -0.05
    POSITIVE LOGITS
     kepada
    0.07
    Units
    0.07
     Bylo
    0.07
    åĩºåİ»
    0.07
    adena
    0.07
     veniam
    0.07
     Tickets
    0.07
     Au
    0.07
    reten
    0.07
     tickets
    0.07
    Activations Density 0.065%

    No Known Activations