© 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. 86088
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to data import and integration systems

    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
    uras
    -0.06
    MSN
    -0.06
    seau
    -0.06
    ars
    -0.06
    pering
    -0.06
    Deferred
    -0.06
     cert
    -0.06
    273
    -0.06
     Blue
    -0.06
     Kling
    -0.06
    POSITIVE LOGITS
     automatically
    0.08
    autom
    0.08
    ushman
    0.08
     automáticamente
    0.08
    ola
    0.07
    KHR
    0.07
    agli
    0.07
    ãĥIJãĥ¼
    0.07
     automatic
    0.07
    lla
    0.07
    Activations Density 0.011%

    No Known Activations