© 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. 27794
    Prev
    Next
    INDEX
    Explanations

    keywords related to health and wellness policies

    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
    æ²»
    -0.07
    appa
    -0.07
     Perf
    -0.06
    Lens
    -0.06
    åŃ
    -0.06
    innamon
    -0.06
     Marker
    -0.06
    oop
    -0.06
    rego
    -0.06
    orate
    -0.05
    POSITIVE LOGITS
    кав
    0.08
     introduced
    0.07
    curity
    0.07
    ливÑĸ
    0.07
    _REPLACE
    0.07
     pal
    0.06
     Introduced
    0.06
     cal
    0.06
     healthier
    0.06
    ado
    0.06
    Activations Density 0.010%

    No Known Activations