© 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. 5222
    Prev
    Next
    INDEX
    Explanations

    phrases discussing options or choices in relation to functionality

    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
    iales
    -0.07
    ripper
    -0.07
    âĦĸâĦĸ
    -0.06
    TRACE
    -0.06
    .webdriver
    -0.06
    ære
    -0.06
    rench
    -0.06
    endas
    -0.06
     bit
    -0.06
     unofficial
    -0.06
    POSITIVE LOGITS
    usta
    0.07
    cation
    0.07
    ocket
    0.07
    arus
    0.07
     users
    0.06
    ÑĤÑı
    0.06
    ewan
    0.06
    Tube
    0.06
    ubar
    0.06
     ìĨĮ리
    0.06
    Activations Density 0.001%

    No Known Activations