© 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. 98366
    Prev
    Next
    INDEX
    Explanations

    terms related to HIV and its prevalence or infection rates

    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
    enge
    -0.07
     Kons
    -0.06
    abei
    -0.06
    oton
    -0.06
    incinn
    -0.06
    emmel
    -0.06
    _VIRTUAL
    -0.06
    997
    -0.06
    idl
    -0.06
    âĢ¦but
    -0.06
    POSITIVE LOGITS
     Recon
    0.07
    OfFile
    0.07
    adic
    0.06
    _reporting
    0.06
    obl
    0.06
    ayscale
    0.06
     Kay
    0.06
     Ïĥελ
    0.06
     miss
    0.06
    ricks
    0.06
    Activations Density 0.003%

    No Known Activations