© 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. 79806
    Prev
    Next
    INDEX
    Explanations

    expressions of positive feelings and appreciation

    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
    airo
    -0.08
    imizer
    -0.07
    conexao
    -0.06
    else
    -0.06
    uring
    -0.06
    );?>↵
    -0.06
    ĸ
    -0.06
    ampa
    -0.06
    EFAULT
    -0.06
    inp
    -0.06
    POSITIVE LOGITS
     thereof
    0.08
     ello
    0.07
    stal
    0.07
    assel
    0.07
    ictionary
    0.07
     dabei
    0.07
     accordingly
    0.07
     doing
    0.07
    íĤ
    0.07
    gel
    0.06
    Activations Density 0.033%

    No Known Activations