© 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. 62456
    Prev
    Next
    INDEX
    Explanations

    elements related to authenticity and cultural experiences

    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
    isku
    -0.07
    SSERT
    -0.07
     stron
    -0.07
    raw
    -0.07
    illez
    -0.07
    ÙĪد
    -0.06
    ideshow
    -0.06
    fuck
    -0.06
     Cra
    -0.06
    aza
    -0.06
    POSITIVE LOGITS
    ennon
    0.07
     cres
    0.06
    tring
    0.06
    iyah
    0.06
     Pride
    0.06
    oise
    0.06
     different
    0.06
     Nose
    0.06
     activities
    0.06
    791
    0.05
    Activations Density 0.010%

    No Known Activations