© 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. 86059
    Prev
    Next
    INDEX
    Explanations

    mentions of experimental procedures and results related to viral infections in laboratory animals

    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
     Pill
    -0.07
    ìĻķ
    -0.07
    tvrt
    -0.06
    quat
    -0.06
     Crosby
    -0.06
    wat
    -0.06
    yntax
    -0.06
    -pill
    -0.06
    åº
    -0.06
    ie
    -0.06
    POSITIVE LOGITS
     presentation
    0.08
     antigen
    0.08
     stimuli
    0.07
     allerg
    0.07
     antig
    0.07
    Sad
    0.07
     Stim
    0.07
    resentation
    0.07
    indsight
    0.07
    -present
    0.07
    Activations Density 0.022%

    No Known Activations