© 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. 83575
    Prev
    Next
    INDEX
    Explanations

    terms related to nuclear systems and their complexities

    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
    _consts
    -0.07
    cie
    -0.06
    acos
    -0.06
     rak
    -0.06
    itol
    -0.06
    âĢ¦↵
    -0.06
    ipel
    -0.06
    omm
    -0.06
     Moor
    -0.06
    éłĨ
    -0.06
    POSITIVE LOGITS
    -wide
    0.07
    .snap
    0.07
    oggler
    0.07
    ëıĮ
    0.07
    بد
    0.07
    ERGY
    0.07
    UnderTest
    0.07
    wide
    0.06
    napshot
    0.06
     Farrell
    0.06
    Activations Density 0.039%

    No Known Activations