© 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. 116892
    Prev
    Next
    INDEX
    Explanations

    visibility qualifiers in programming code, specifically related to access modifiers

    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
    æįķ
    -0.07
    resse
    -0.07
    uli
    -0.07
    ioc
    -0.07
    121
    -0.06
    iv
    -0.06
    ose
    -0.06
     Göz
    -0.06
    ub
    -0.06
    øj
    -0.06
    POSITIVE LOGITS
    anges
    0.07
    à§į
    0.06
    urved
    0.06
     aut
    0.06
    ¯¯
    0.05
    gebn
    0.05
    .swt
    0.05
    γή
    0.05
    ybrid
    0.05
    kdir
    0.05
    Activations Density 0.002%

    No Known Activations