© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 9-LLAMASCOPE-RES-131K
    11. 96673
    Prev
    Next
    INDEX
    Explanations

    concepts related to copying and duplication of materials

    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
    lse
    -0.06
    ocrates
    -0.06
    ãĥ©ãĥ³ãĥī
    -0.06
    ↵
    -0.05
     un
    -0.05
     premise
    -0.05
    auer
    -0.05
     logo
    -0.05
    ons
    -0.05
    '
    -0.05
    POSITIVE LOGITS
    endcode
    0.09
    /cop
    0.08
     copies
    0.08
    館
    0.08
     Haram
    0.07
    opia
    0.07
    é¦Ĩ
    0.07
    shadow
    0.07
    braco
    0.07
    uary
    0.07
    Activations Density 0.017%

    No Known Activations