© 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. 81885
    Prev
    Next
    INDEX
    Explanations

    instances of events that are organized or sponsored

    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
    agar
    -0.07
    anium
    -0.06
    enders
    -0.06
    uento
    -0.06
     rect
    -0.06
    rit
    -0.06
    ÙĪÙĩ
    -0.06
    ND
    -0.06
     sist
    -0.05
    bit
    -0.05
    POSITIVE LOGITS
    Frameworks
    0.08
    ller
    0.08
    :variables
    0.07
     تÙĪسط
    0.07
    ntag
    0.07
    itele
    0.07
     Vere
    0.07
    yla
    0.07
    antz
    0.07
    swer
    0.07
    Activations Density 0.011%

    No Known Activations