© 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. 72939
    Prev
    Next
    INDEX
    Explanations

    assignment statements and object property 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
    awning
    -0.06
    emed
    -0.06
    elon
    -0.06
     Pip
    -0.06
     Helm
    -0.06
    arge
    -0.06
    raig
    -0.06
     helmet
    -0.06
     Kirby
    -0.06
    umpt
    -0.05
    POSITIVE LOGITS
    ownik
    0.07
    Å¡e
    0.07
     ifndef
    0.07
    atz
    0.07
    ":{↵
    0.07
    pcodes
    0.06
    }{↵
    0.06
    estion
    0.06
     ëĺIJ
    0.06
    013
    0.06
    Activations Density 0.010%

    No Known Activations