© 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. 121224
    Prev
    Next
    INDEX
    Explanations

    expressions of personal enjoyment and affection

    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
    urette
    -0.07
    ypy
    -0.07
    burger
    -0.07
    htub
    -0.07
    rette
    -0.07
    é¨ĵ
    -0.06
    alez
    -0.06
    LiveData
    -0.06
    abit
    -0.06
     naveg
    -0.06
    POSITIVE LOGITS
     anthrop
    0.06
     English
    0.06
    English
    0.06
    insky
    0.06
    ìĸ¸
    0.06
     sized
    0.06
     Him
    0.06
     Hague
    0.05
    çIJ³
    0.05
     whe
    0.05
    Activations Density 0.001%

    No Known Activations