© 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. 84214
    Prev
    Next
    INDEX
    Explanations

    references to post-modern 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
    lech
    -0.08
    ormsg
    -0.08
    Âłje
    -0.07
    udu
    -0.07
    jmu
    -0.07
    âĢ¦↵↵↵
    -0.07
    ndon
    -0.07
    immune
    -0.07
    åķª
    -0.07
    lius
    -0.07
    POSITIVE LOGITS
    /post
    0.07
    ward
    0.07
    agram
    0.06
    ery
    0.06
     shuttle
    0.06
    vero
    0.06
    ulates
    0.06
    ubby
    0.06
     Shuttle
    0.06
    -
    0.06
    Activations Density 0.010%

    No Known Activations