© 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. 15-LLAMASCOPE-RES-131K
    11. 104163
    Prev
    Next
    INDEX
    Explanations

    references to plagiarism detection and publication ethics tools

    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
    .rmi
    -0.07
    vrier
    -0.07
    ylim
    -0.07
    å®Ļ
    -0.06
    oine
    -0.06
     tend
    -0.06
    pson
    -0.06
    uries
    -0.06
    inet
    -0.06
    ÃŃsticas
    -0.06
    POSITIVE LOGITS
    deÅŁ
    0.07
    undan
    0.07
    ãĥ³ãĥģ
    0.06
     Brow
    0.06
    relay
    0.06
    YNC
    0.06
    Å¡em
    0.06
    à¸Ńà¸Ļà¸Ĺ
    0.06
    iper
    0.06
    ROUGH
    0.06
    Activations Density 0.001%

    No Known Activations