© 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. 129961
    Prev
    Next
    INDEX
    Explanations

    terms related to conditions, classifications, and eligibility criteria

    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
    uran
    -0.06
    lap
    -0.06
    essler
    -0.06
     Shelf
    -0.06
    SSERT
    -0.06
     shelf
    -0.06
    æk
    -0.06
    alleries
    -0.06
     Schro
    -0.05
    ura
    -0.05
    POSITIVE LOGITS
     basis
    0.11
    basis
    0.09
     situation
    0.08
     Basis
    0.08
     circumstances
    0.07
     case
    0.07
     situations
    0.07
    æĥħåĨµ
    0.07
     BASIS
    0.07
     cases
    0.07
    Activations Density 0.002%

    No Known Activations