© 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. 104464
    Prev
    Next
    INDEX
    Explanations

    phrases and clauses indicating necessity or expectation

    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
    ãģ¾ãģļ
    -0.08
    ازÛĮ
    -0.07
    WARDED
    -0.07
    _*
    -0.07
     Firstly
    -0.07
    ERCHANT
    -0.07
    âķĹ
    -0.07
    ÑĪе
    -0.06
    enders
    -0.06
    nero
    -0.06
    POSITIVE LOGITS
     therefore
    0.11
     consequently
    0.09
    ãģ¾ãģŁ
    0.08
     quindi
    0.08
     Therefore
    0.08
    Therefore
    0.07
     accordingly
    0.07
     hence
    0.06
     there
    0.06
    otland
    0.06
    Activations Density 0.018%

    No Known Activations