© 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. 17-LLAMASCOPE-RES-131K
    11. 39495
    Prev
    Next
    INDEX
    Explanations

    scientific classifications and metrics related to viruses

    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
     fred
    -0.07
    /release
    -0.07
    /pub
    -0.06
    eyh
    -0.06
    fred
    -0.06
    MAS
    -0.06
    ãĥ«ãĤ¯
    -0.06
    ?a
    -0.06
    uve
    -0.06
    unker
    -0.06
    POSITIVE LOGITS
    rawn
    0.07
     há»Ļi
    0.06
    åŀ
    0.06
     ekip
    0.06
    endants
    0.06
     disadv
    0.06
    ÙĪاء
    0.06
    engers
    0.06
    andalone
    0.06
     меÑĪ
    0.06
    Activations Density 0.034%

    No Known Activations