© 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. 28224
    Prev
    Next
    INDEX
    Explanations

    key subjects and their relationships within complex arguments and narratives

    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
    hol
    -0.06
     number
    -0.06
    led
    -0.06
     nackte
    -0.06
    عÙĬ
    -0.06
    inci
    -0.06
     part
    -0.06
     pace
    -0.06
    ib
    -0.06
     factor
    -0.06
    POSITIVE LOGITS
    òn
    0.08
    à¹ģà¸Ļ
    0.07
    othy
    0.07
    еÑĢеж
    0.07
    amedi
    0.07
    ocht
    0.07
    ruptions
    0.07
    kaar
    0.07
    WithDuration
    0.07
    asiswa
    0.07
    Activations Density 0.041%

    No Known Activations