© 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. 76836
    Prev
    Next
    INDEX
    Explanations

    instances of copyright symbols

    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
    eron
    -0.07
    ÑĢÑĥÑĩ
    -0.07
    olt
    -0.07
    ml
    -0.06
    zon
    -0.06
    are
    -0.06
    оÑĤов
    -0.06
    ero
    -0.06
    yan
    -0.06
    iti
    -0.06
    POSITIVE LOGITS
    ï¸ı
    0.19
    ï¸
    0.13
     Copyright
    0.08
    ©©
    0.08
    Copyright
    0.08
    /***/
    0.08
     copyright
    0.07
    groundColor
    0.07
     COPYRIGHT
    0.07
    icas
    0.07
    Activations Density 0.007%

    No Known Activations