© 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. 107641
    Prev
    Next
    INDEX
    Explanations

    phrases indicating travel routes between Naples and Rome

    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
    зÑĥ
    -0.07
    ë¹Ļ
    -0.07
    luluk
    -0.07
    egie
    -0.07
    omon
    -0.07
    нез
    -0.07
    ierz
    -0.06
    obus
    -0.06
     Rifle
    -0.06
     nét
    -0.06
    POSITIVE LOGITS
    erva
    0.07
    ugal
    0.06
    inker
    0.06
    Magnitude
    0.06
     asn
    0.06
     Sachs
    0.06
     вдÑĢÑĥг
    0.06
    ENU
    0.05
    ovu
    0.05
    adian
    0.05
    Activations Density 0.002%

    No Known Activations