© 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. 117216
    Prev
    Next
    INDEX
    Explanations

    occurrences of the phrase "in" related to various contexts, particularly durations and events

    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
    .qual
    -0.06
     sparing
    -0.06
    ebin
    -0.06
     ÑģилÑĥ
    -0.06
    orda
    -0.06
    äch
    -0.06
    aver
    -0.06
    argo
    -0.06
     fet
    -0.06
     moment
    -0.06
    POSITIVE LOGITS
    ä¹³
    0.06
    conto
    0.06
     Tucker
    0.06
    icken
    0.06
    onya
    0.06
     Apostle
    0.06
    riel
    0.06
    thers
    0.06
    render
    0.06
    onds
    0.06
    Activations Density 0.013%

    No Known Activations