© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 59632
    Prev
    Next
    INDEX
    Explanations

    prepositions indicating authorship or origin

    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
    its
    -0.07
     behalf
    -0.06
    pany
    -0.06
     Odyssey
    -0.06
    ode
    -0.06
    ëĮĢë¡ľ
    -0.06
    just
    -0.06
    clus
    -0.06
     Dud
    -0.05
    nob
    -0.05
    POSITIVE LOGITS
    uyla
    0.10
     far
    0.08
    tÄĽ
    0.08
     definition
    0.08
    aucoup
    0.08
    larak
    0.08
    tring
    0.08
    TestFixture
    0.08
    gone
    0.08
    _marshall
    0.07
    Activations Density 0.004%

    No Known Activations