© 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. 61761
    Prev
    Next
    INDEX
    Explanations

    key components and phases related to project management and engineering design

    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
    lied
    -0.07
    659
    -0.07
     overhead
    -0.07
    uga
    -0.07
    531
    -0.06
     infra
    -0.06
    idia
    -0.06
    Preferences
    -0.06
    ç´Ģ
    -0.06
     пал
    -0.06
    POSITIVE LOGITS
    .bunifuFlatButton
    0.08
    acers
    0.07
    ettle
    0.07
     заклад
    0.07
    اÙĤÙĦ
    0.07
    odb
    0.07
     Pass
    0.07
    steam
    0.06
    è¹
    0.06
    specifier
    0.06
    Activations Density 0.006%

    No Known Activations