© 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. 70617
    Prev
    Next
    INDEX
    Explanations

    terms related to plagiarism and source attribution

    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
    |max
    -0.06
     Doe
    -0.06
    gv
    -0.06
    èĬ
    -0.06
    xC
    -0.06
     Dove
    -0.06
     signific
    -0.05
    nze
    -0.05
    èģ
    -0.05
    ded
    -0.05
    POSITIVE LOGITS
     source
    0.19
     sources
    0.18
     Sources
    0.16
    source
    0.16
     Source
    0.15
     SOURCE
    0.15
    sources
    0.15
    -source
    0.14
     getSource
    0.14
    _Source
    0.14
    Activations Density 0.029%

    No Known Activations