© 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. 15-LLAMASCOPE-RES-131K
    11. 88141
    Prev
    Next
    INDEX
    Explanations

    occurrences of specific character names or roles in a script or narrative

    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
    ApplicationBuilder
    -0.08
    allis
    -0.08
     ifndef
    -0.07
    ùa
    -0.07
     Throne
    -0.07
    ForResource
    -0.07
    åľ¨çº¿éĺħ读
    -0.07
    abyrin
    -0.07
    CppClass
    -0.07
     éĸ¢éĢ£
    -0.07
    POSITIVE LOGITS
     amb
    0.06
     lo
    0.05
     oneself
    0.05
     himself
    0.05
     inf
    0.05
    attered
    0.05
     conn
    0.05
     nar
    0.05
     spread
    0.05
    hem
    0.05
    Activations Density 0.001%

    No Known Activations