© 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. 108291
    Prev
    Next
    INDEX
    Explanations

    references to political figures or titles

    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
    aldi
    -0.08
    ["$
    -0.08
     ä½IJ
    -0.07
     зов
    -0.07
    redo
    -0.07
    ãĥģãĥ¥
    -0.07
    oling
    -0.07
    igue
    -0.07
    lte
    -0.07
    lay
    -0.07
    POSITIVE LOGITS
    114
    0.06
    110
    0.06
    662
    0.06
    طر
    0.06
     jun
    0.06
    115
    0.06
     gut
    0.06
    âĹİ
    0.06
     vis
    0.06
     Mr
    0.06
    Activations Density 0.003%

    No Known Activations