© 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. 9-LLAMASCOPE-RES-131K
    11. 98150
    Prev
    Next
    INDEX
    Explanations

    phrases that suggest visualization or hypothetical scenarios

    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
    eczy
    -0.07
    getManager
    -0.06
    gov
    -0.06
    imon
    -0.06
    unge
    -0.06
    èIJ
    -0.06
    ollen
    -0.06
    обов
    -0.06
    mos
    -0.06
    enser
    -0.06
    POSITIVE LOGITS
    Cheap
    0.06
     Sweep
    0.06
     Bates
    0.06
    erdale
    0.06
     آس
    0.06
    cus
    0.06
    ergy
    0.06
    **/↵↵
    0.05
    ìĭĿ
    0.05
    TEGER
    0.05
    Activations Density 0.005%

    No Known Activations