© 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. 93838
    Prev
    Next
    INDEX
    Explanations

    specific Unicode characters or symbols

    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
     å£
    -0.09
    æŶåĢĻ
    -0.08
    ibold
    -0.08
    ity
    -0.07
    ITY
    -0.07
    atsu
    -0.07
    ed
    -0.07
    kop
    -0.06
     Playground
    -0.06
    allis
    -0.06
    POSITIVE LOGITS
    onen
    0.07
     mum
    0.06
    essen
    0.06
    chedulers
    0.06
    -fold
    0.06
    hes
    0.06
    han
    0.06
    تا
    0.06
    nnen
    0.06
     Harr
    0.06
    Activations Density 0.001%

    No Known Activations