© 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. 9-LLAMASCOPE-RES-131K
    11. 94659
    Prev
    Next
    INDEX
    Explanations

    references to organizational entities and brands in a corporate context

    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
    ym
    -0.06
    edii
    -0.06
     Suites
    -0.06
    ulen
    -0.06
    PathComponent
    -0.06
    omic
    -0.06
    ont
    -0.06
    eries
    -0.06
    ContextHolder
    -0.06
     inst
    -0.06
    POSITIVE LOGITS
     Lump
    0.07
     dikke
    0.07
    âĢIJâĢIJ
    0.07
    пи
    0.07
    izard
    0.07
    é»ĺ
    0.07
     meisjes
    0.07
    -spin
    0.07
    벤
    0.07
     mooie
    0.06
    Activations Density 0.038%

    No Known Activations