© 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. 82069
    Prev
    Next
    INDEX
    Explanations

    actions related to the establishment and construction of organizations or structures

    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
     mik
    -0.06
     tub
    -0.06
    oga
    -0.05
     weg
    -0.05
    asting
    -0.05
    olls
    -0.05
    ëłµ
    -0.05
    rieg
    -0.05
    dea
    -0.05
    asts
    -0.05
    POSITIVE LOGITS
    OrUpdate
    0.08
     напÑĢи
    0.08
    iert
    0.08
    edar
    0.07
     Äijá»ĥ
    0.07
    TestCategory
    0.07
    isini
    0.07
    TRL
    0.07
    etten
    0.07
    kan
    0.07
    Activations Density 0.036%

    No Known Activations