© 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. 92785
    Prev
    Next
    INDEX
    Explanations

    references to quality and standards in professional services

    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
    _________________↵↵
    -0.09
     Tüm
    -0.09
    .DropDown
    -0.09
     Kız
    -0.08
    اصÙĦÙĩ
    -0.08
    .Mapping
    -0.08
    ologne
    -0.08
    νοÏį
    -0.08
    ãģıãģł
    -0.08
     )↵↵↵↵↵↵↵↵
    -0.08
    POSITIVE LOGITS
     wil
    0.07
    mî
    0.07
    ..↵
    0.06
    rush
    0.06
     ..
    0.06
    omi
    0.06
    Ease
    0.06
     søger
    0.05
    bler
    0.05
    312
    0.05
    Activations Density 0.932%

    No Known Activations