© 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. 9-LLAMASCOPE-RES-131K
    11. 94602
    Prev
    Next
    INDEX
    Explanations

    information related to connectivity features in devices

    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
    cil
    -0.07
    rts
    -0.06
    ETO
    -0.06
    ?.
    -0.06
    hurst
    -0.06
    ุม
    -0.06
    imon
    -0.06
    metis
    -0.06
    hydr
    -0.06
    hof
    -0.06
    POSITIVE LOGITS
    ÃĹ↵↵
    0.07
    EMPLARY
    0.06
    ÏĢοί
    0.06
    ellar
    0.06
     nth
    0.06
    ouri
    0.06
    recision
    0.06
     Fo
    0.06
     TRACE
    0.06
    927
    0.06
    Activations Density 0.005%

    No Known Activations