© 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. 27308
    Prev
    Next
    INDEX
    Explanations

    instances of conditional statements or qualifications

    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
     alike
    -0.08
    ipherals
    -0.07
    ansa
    -0.06
    RT
    -0.06
    itsu
    -0.06
    libs
    -0.06
    abajo
    -0.06
    anda
    -0.06
    ipheral
    -0.06
    ifter
    -0.06
    POSITIVE LOGITS
    anean
    0.07
     INCIDENTAL
    0.07
    loff
    0.07
    enson
    0.07
     BAT
    0.06
     мов
    0.06
    gan
    0.06
    ãĥ¼ãĤ¿ãĥ¼
    0.06
    BAT
    0.06
    lea
    0.06
    Activations Density 0.000%

    No Known Activations