© 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. 131068
    Prev
    Next
    INDEX
    Explanations

    technical terms related to programming and data processing

    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
    ourg
    -0.07
    rof
    -0.07
    tout
    -0.07
    jur
    -0.07
     addCriterion
    -0.07
     Straw
    -0.06
    afil
    -0.06
    ContextHolder
    -0.06
    okie
    -0.06
     ç§ĭ
    -0.06
    POSITIVE LOGITS
     instance
    0.06
     instanceof
    0.06
    brid
    0.06
    lsi
    0.06
    aras
    0.06
     gem
    0.06
    对象
    0.06
    186
    0.06
    obj
    0.06
    428
    0.06
    Activations Density 0.100%

    No Known Activations