© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 105706
    Prev
    Next
    INDEX
    Explanations

    sequences of numerical values or data structures

    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
    donnees
    -0.07
    ÃŃs
    -0.06
    anske
    -0.06
    ain
    -0.06
     (::
    -0.06
     mighty
    -0.06
     kennen
    -0.06
    Ư
    -0.06
    illed
    -0.06
    chos
    -0.06
    POSITIVE LOGITS
     etc
    0.08
    елиÑĩ
    0.07
     //
    0.07
     ...(
    0.07
    ureau
    0.07
    asca
    0.07
     /**↵
    0.07
    wich
    0.06
    ãĥ¡ãĥ³ãĥĪ
    0.06
    vais
    0.06
    Activations Density 0.025%

    No Known Activations