© 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. 120548
    Prev
    Next
    INDEX
    Explanations

    instances of the preposition "par"

    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
    endencies
    -0.08
    ocaly
    -0.08
    eyim
    -0.08
    amik
    -0.08
     NÄĽkter
    -0.08
    _mB
    -0.08
     Helvetica
    -0.07
    ustil
    -0.07
    ãĤ»ãĥ³
    -0.07
    daÅŁ
    -0.07
    POSITIVE LOGITS
     convention
    0.07
    ro
    0.07
     means
    0.07
    rd
    0.07
    aus
    0.06
     force
    0.06
    phy
    0.06
    ly
    0.06
    tridge
    0.06
    anko
    0.06
    Activations Density 0.005%

    No Known Activations