© 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. 62804
    Prev
    Next
    INDEX
    Explanations

    technical specifications and functional details of devices

    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
    DDS
    -0.06
    emem
    -0.06
    alla
    -0.06
    ARB
    -0.06
    ÛĮات
    -0.06
     Offensive
    -0.06
    oyo
    -0.06
    -neutral
    -0.06
     offensive
    -0.06
    à¹ĥ
    -0.05
    POSITIVE LOGITS
     triggering
    0.09
     trigger
    0.08
    trigger
    0.08
    Trigger
    0.08
    -trigger
    0.08
     Trigger
    0.08
    (trigger
    0.07
     motion
    0.07
    Threshold
    0.07
    .trigger
    0.07
    Activations Density 0.016%

    No Known Activations