© 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. 3632
    Prev
    Next
    INDEX
    Explanations

    references to viruses and biological threats

    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
    .scalablytyped
    -0.08
     Marble
    -0.07
    èĩº
    -0.07
    ảnh
    -0.07
    ÏĥÏĥ
    -0.07
    Ïĥή
    -0.07
    ships
    -0.07
    ÑĢеб
    -0.07
    ignum
    -0.06
    utters
    -0.06
    POSITIVE LOGITS
     crown
    0.07
    uzzi
    0.06
     Nature
    0.06
     Nat
    0.06
    ifr
    0.06
    frau
    0.06
    wald
    0.06
    adolu
    0.06
     origin
    0.05
     Gos
    0.05
    Activations Density 0.005%

    No Known Activations