© 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. 69430
    Prev
    Next
    INDEX
    Explanations

    references to geographical locations, particularly islands

    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
    ãĥ§
    -0.09
    EMPLARY
    -0.07
    ÑĮ
    -0.07
     indeb
    -0.07
    ilib
    -0.07
    iface
    -0.06
    ville
    -0.06
    nze
    -0.06
    .FC
    -0.06
    /GPL
    -0.06
    POSITIVE LOGITS
    ait
    0.07
    ITERAL
    0.07
    enario
    0.07
    inois
    0.07
    ARNING
    0.07
    otten
    0.06
    Äįan
    0.06
    erman
    0.06
    osph
    0.06
    umin
    0.06
    Activations Density 0.002%

    No Known Activations