© 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. 73982
    Prev
    Next
    INDEX
    Explanations

    key elements related to educational tasks and performance indicators

    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
     Nin
    -0.07
     MetroFramework
    -0.06
    anager
    -0.05
     Tro
    -0.05
    eldon
    -0.05
    utf
    -0.05
    onymous
    -0.05
    idge
    -0.05
     Tim
    -0.05
    rych
    -0.05
    POSITIVE LOGITS
    0.08
    ãĤ¾
    0.07
    TypeEnum
    0.07
     èĮ
    0.07
    udeau
    0.07
    .getExternal
    0.07
    ìĨĮê°ľ
    0.07
    mith
    0.07
    cket
    0.07
    vik
    0.07
    Activations Density 0.001%

    No Known Activations