© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 22-LLAMASCOPE-RES-131K
    6. 3829
    Prev
    Next
    INDEX
    Explanations

    repeated usage of the word 'the' and its context in the document

    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
    enek
    -0.08
    undry
    -0.07
    ioni
    -0.07
    _Report
    -0.06
    illard
    -0.06
    æİĽ
    -0.06
    .Deserialize
    -0.06
     difference
    -0.06
     Difference
    -0.06
    elop
    -0.06
    POSITIVE LOGITS
     scene
    0.12
     fold
    0.12
     confines
    0.11
     premises
    0.11
     vicinity
    0.09
     nest
    0.09
     Fold
    0.09
     employ
    0.09
    scene
    0.08
     ranks
    0.08
    Activations Density 0.031%

    No Known Activations