© 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. 81000
    Prev
    Next
    INDEX
    Explanations

    acronyms or abbreviations typically used in professional or technical contexts

    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
    оваÑĢи
    -0.07
     PartialView
    -0.07
    arten
    -0.07
    adle
    -0.06
     Reed
    -0.06
    éro
    -0.06
    ashes
    -0.06
    imals
    -0.06
    arez
    -0.06
     treff
    -0.06
    POSITIVE LOGITS
    xygen
    0.08
    iqu
    0.08
    led
    0.07
    636
    0.07
    rou
    0.07
    een
    0.06
    scan
    0.06
    mess
    0.06
    çĭIJ
    0.06
    anan
    0.06
    Activations Density 0.043%

    No Known Activations