© 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. 120390
    Prev
    Next
    INDEX
    Explanations

    themes related to physical and emotional experiences involving risk-taking and loyalty

    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
    abet
    -0.07
    ilt
    -0.07
    empo
    -0.07
    ÑĤен
    -0.07
    isia
    -0.07
    ventus
    -0.07
    irut
    -0.07
    ÙĨب
    -0.07
    à¹ĥà¸Ī
    -0.07
    inese
    -0.07
    POSITIVE LOGITS
    Rx
    0.06
    rx
    0.06
    581
    0.06
    432
    0.06
     Rwanda
    0.06
     en
    0.06
    513
    0.06
    /business
    0.06
    ight
    0.05
    idad
    0.05
    Activations Density 0.049%

    No Known Activations