© 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. 82314
    Prev
    Next
    INDEX
    Explanations

    instances of the word "and" frequently used in various contexts

    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
    arer
    -0.08
    OrElse
    -0.08
    mpr
    -0.07
    WithPath
    -0.07
    ýt
    -0.07
    رÙħ
    -0.07
    plier
    -0.07
    ãĥĥãĥĦ
    -0.07
    овеÑĢ
    -0.06
    оÑĢаз
    -0.06
    POSITIVE LOGITS
    avad
    0.07
    065
    0.07
    /or
    0.07
    Question
    0.06
    074
    0.06
    .Stretch
    0.06
     )↵↵↵↵↵↵↵↵
    0.06
    wie
    0.06
    omain
    0.06
    iero
    0.06
    Activations Density 0.020%

    No Known Activations