© 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. 40385
    Prev
    Next
    INDEX
    Explanations

    words and phrases indicating success in complex situations

    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
    emme
    -0.08
    etro
    -0.07
    isd
    -0.07
     вÑĩ
    -0.07
     окÑĤ
    -0.07
     yesterday
    -0.07
     //<
    -0.07
    eldon
    -0.07
    imu
    -0.07
    کات
    -0.07
    POSITIVE LOGITS
    ogne
    0.07
    ocker
    0.06
     inland
    0.06
     {?>↵
    0.06
     a
    0.06
     eventually
    0.06
    roc
    0.06
    iggers
    0.05
    BITS
    0.05
     various
    0.05
    Activations Density 0.001%

    No Known Activations