© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 75273
    Prev
    Next
    INDEX
    Explanations

    instances of object-oriented programming concepts, particularly related to class attributes and methods

    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
    LETE
    -0.06
    io
    -0.06
     Nar
    -0.06
     Bowman
    -0.06
    .arguments
    -0.06
    niÄį
    -0.06
    lor
    -0.06
    rier
    -0.06
    675
    -0.05
    olk
    -0.05
    POSITIVE LOGITS
    redo
    0.07
    ————————————————
    0.07
    ————————
    0.07
    kou
    0.07
    abei
    0.06
    edes
    0.06
    jeta
    0.06
     Depth
    0.06
    Parcelable
    0.06
    ÑĮе
    0.06
    Activations Density 0.015%

    No Known Activations