© 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. 57569
    Prev
    Next
    INDEX
    Explanations

    key terms and entities associated with health, governance, and ecosystem discussions

    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
    иÑĤ
    -0.06
    .Percent
    -0.06
    ElementException
    -0.06
    adiens
    -0.05
    contro
    -0.05
    д
    -0.05
    impl
    -0.05
    oufl
    -0.05
     elapsed
    -0.05
    LTRB
    -0.05
    POSITIVE LOGITS
     SavaÅŁ
    0.07
    ÑĢади
    0.07
    надлеж
    0.07
     ekran
    0.07
    ЯкÑīо
    0.07
    Як
    0.07
     toi
    0.07
    наÑģлÑĸд
    0.06
     Oyun
    0.06
    оÑģÑĤаÑĤ
    0.06
    Activations Density 0.011%

    No Known Activations