© 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. 93266
    Prev
    Next
    INDEX
    Explanations

    references to roles, administrative structures, and processes related to governance or organization

    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
    çIJ³
    -0.07
    lix
    -0.06
    jerne
    -0.06
    ieee
    -0.06
    ãģķãģ¾
    -0.06
    ksiyon
    -0.06
    PRS
    -0.06
    alo
    -0.06
    رخ
    -0.06
    137
    -0.06
    POSITIVE LOGITS
    .scalablytyped
    0.09
     Shall
    0.07
     shall
    0.06
    \OptionsResolver
    0.06
     SHALL
    0.06
    shall
    0.06
     пÑĥÑĤ
    0.06
    _AUT
    0.06
    usp
    0.06
    utters
    0.06
    Activations Density 0.003%

    No Known Activations