© 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. 85795
    Prev
    Next
    INDEX
    Explanations

    terms related to object-oriented programming and method definitions in code

    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
    ä¼
    -0.07
    bert
    -0.07
    oco
    -0.06
    amma
    -0.06
    amburger
    -0.06
    ÑĥÑĤи
    -0.06
    nest
    -0.06
    éģº
    -0.06
    lrt
    -0.06
    -urlencoded
    -0.06
    POSITIVE LOGITS
     other
    0.11
     another
    0.10
     fellow
    0.10
    (other
    0.09
    qv
    0.09
     anderen
    0.09
     andere
    0.09
    another
    0.09
    -other
    0.09
     altro
    0.09
    Activations Density 0.016%

    No Known Activations