© 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. 9-LLAMASCOPE-RES-131K
    11. 98359
    Prev
    Next
    INDEX
    Explanations

    geographical locations and names associated with individuals

    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
    Ñij
    -0.07
     Singleton
    -0.06
    ERP
    -0.06
    pps
    -0.06
    ebe
    -0.06
    Ñĩ
    -0.06
     Freddie
    -0.06
     rencontrer
    -0.06
     Saud
    -0.06
    fed
    -0.06
    POSITIVE LOGITS
    tica
    0.08
    AYOUT
    0.07
    aldi
    0.07
    immel
    0.07
     compl
    0.06
    horia
    0.06
    orias
    0.06
     Clover
    0.06
    093
    0.06
    eldo
    0.06
    Activations Density 0.002%

    No Known Activations