© 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. 17-LLAMASCOPE-RES-131K
    11. 93885
    Prev
    Next
    INDEX
    Explanations

    mentions of open data and accessibility initiatives

    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
    orf
    -0.07
    ãģĭãģª
    -0.07
    azar
    -0.07
    webtoken
    -0.06
    _sdk
    -0.06
    ientes
    -0.06
     æĸĩç«ł
    -0.06
    adÃŃ
    -0.06
    aye
    -0.06
    tae
    -0.06
    POSITIVE LOGITS
     public
    0.09
     citizen
    0.09
     Public
    0.09
     citizens
    0.08
    odata
    0.08
     government
    0.08
     Citizen
    0.08
    public
    0.08
     data
    0.07
    .public
    0.07
    Activations Density 0.009%

    No Known Activations