© 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. 81721
    Prev
    Next
    INDEX
    Explanations

    technical language related to computer systems and their operations

    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
    rms
    -0.06
     Static
    -0.06
    pac
    -0.06
    ãĥ¬ãĥ³
    -0.06
    зм
    -0.06
     recipro
    -0.06
    BackingField
    -0.06
     ÑĪиÑĢ
    -0.06
    abel
    -0.06
     convictions
    -0.06
    POSITIVE LOGITS
     startup
    0.08
     startups
    0.08
    =start
    0.08
    566
    0.08
     boots
    0.07
     boot
    0.07
    startup
    0.07
    _startup
    0.07
    .login
    0.07
    $start
    0.07
    Activations Density 0.017%

    No Known Activations