© 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. 82178
    Prev
    Next
    INDEX
    Explanations

    instances of the word "in."

    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
    ulumi
    -0.06
    fter
    -0.06
    ãģĨãģ¡
    -0.06
    .readString
    -0.06
     ÑĨим
    -0.06
    .aspx
    -0.06
    omp
    -0.06
     наÑĥк
    -0.06
    ografia
    -0.06
     Kavanaugh
    -0.06
    POSITIVE LOGITS
     a
    0.07
     an
    0.07
    gid
    0.07
    chwitz
    0.06
    utra
    0.06
     recent
    0.06
    æĪ
    0.06
    деÑĢж
    0.06
    inaire
    0.06
    489
    0.06
    Activations Density 0.014%

    No Known Activations