© 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. 87969
    Prev
    Next
    INDEX
    Explanations

    various types of annotations and editorial notations in the text

    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
    iant
    -0.07
    vi
    -0.07
    fty
    -0.06
    ms
    -0.06
    _compat
    -0.06
    owing
    -0.06
    ýt
    -0.06
    vatel
    -0.06
    rat
    -0.06
     hospodáÅĻ
    -0.06
    POSITIVE LOGITS
    /update
    0.07
    £¼
    0.07
     tran
    0.06
     Update
    0.06
     update
    0.06
    ικα
    0.06
     Morr
    0.06
     cla
    0.06
    ADX
    0.06
    _streams
    0.06
    Activations Density 0.003%

    No Known Activations