© 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 EvalsExportsAPI 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. 130668
    Prev
    Next
    INDEX
    Explanations

    expressions of appreciation or affection towards people and concepts

    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
    erson
    -0.08
    /moment
    -0.08
    é»ĺ
    -0.08
    itler
    -0.07
    meni
    -0.07
    oya
    -0.07
    iyim
    -0.07
    ETO
    -0.07
    illions
    -0.07
    изнеÑģ
    -0.07
    POSITIVE LOGITS
    entially
    0.07
     McGill
    0.06
    wick
    0.06
    ıa
    0.06
     Schneider
    0.06
    ouver
    0.06
    Cipher
    0.06
     Fibonacci
    0.06
    áno
    0.06
    Kit
    0.05
    Activations Density 0.020%

    No Known Activations