© 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. 92104
    Prev
    Next
    INDEX
    Explanations

    numerical and reference identifiers in medical or scientific contexts

    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
    anner
    -0.07
    ittings
    -0.07
    yat
    -0.07
    ÑĥÑĤи
    -0.07
    ÄįÃŃ
    -0.06
     Marks
    -0.06
    аÑĢаÑĤ
    -0.06
    SimpleName
    -0.06
    ÂĢÂĢ
    -0.06
    .poly
    -0.06
    POSITIVE LOGITS
     sao
    0.06
    clubs
    0.06
     tall
    0.06
    maj
    0.06
    ola
    0.06
    åª
    0.06
    ;amp
    0.06
     breeze
    0.06
    CEF
    0.06
     ration
    0.06
    Activations Density 0.001%

    No Known Activations