© 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. 107529
    Prev
    Next
    INDEX
    Explanations

    elements related to programming language syntax and class structures

    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
     YÃĸ
    -0.09
    NameValuePair
    -0.08
    ofilm
    -0.08
    okable
    -0.08
    ÙĪÙĨÙĬØ©
    -0.07
    âu
    -0.07
    leck
    -0.07
    portun
    -0.07
    roperty
    -0.07
    /*č↵
    -0.07
    POSITIVE LOGITS
    .plugins
    0.06
     weather
    0.06
    asl
    0.06
    iglia
    0.06
    esto
    0.06
     ï¼
    0.05
    ereo
    0.05
    BX
    0.05
     Westbrook
    0.05
     Grat
    0.05
    Activations Density 0.001%

    No Known Activations