© 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 EvalsExportsinterp-engineNEWAPI 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. 87250
    Prev
    Next
    INDEX
    Explanations

    references to oversight, regulatory bodies, and human rights

    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
    >NN
    -0.07
    виÑĤ
    -0.07
    //*[
    -0.07
    ieres
    -0.07
    ATAL
    -0.07
    icio
    -0.07
    ferences
    -0.07
    aida
    -0.07
    ÑĤÑĮ
    -0.06
    icles
    -0.06
    POSITIVE LOGITS
     rel
    0.07
    eyJ
    0.06
    121
    0.06
    ycastle
    0.06
    inery
    0.06
     for
    0.06
    asca
    0.06
    404
    0.06
    134
    0.06
    ary
    0.06
    Activations Density 0.003%

    No Known Activations