© 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. 58427
    Prev
    Next
    INDEX
    Explanations

    prepositions and their usages in 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
    _ASSUME
    -0.07
    ichel
    -0.07
    RelativeTo
    -0.06
    ondheim
    -0.06
    SupportActionBar
    -0.06
     ли
    -0.06
    _simps
    -0.06
     entity
    -0.06
    ellido
    -0.06
    valuator
    -0.06
    POSITIVE LOGITS
    ï¸ı
    0.07
     typical
    0.06
    Ìģt
    0.06
     sene
    0.06
    lich
    0.06
    ected
    0.06
     اÙħر
    0.06
    _DEFIN
    0.06
     foreground
    0.06
     an
    0.06
    Activations Density 0.010%

    No Known Activations