© 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. 87659
    Prev
    Next
    INDEX
    Explanations

    descriptors of plants and their characteristics

    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
    аниÑĨ
    -0.06
    ãĥ¼ãĥľ
    -0.06
    avenport
    -0.06
     flora
    -0.06
    çĦ¡ãģĹ
    -0.06
    boxed
    -0.06
    /logging
    -0.06
    igin
    -0.06
    ربÙĬØ©
    -0.06
     recep
    -0.06
    POSITIVE LOGITS
    rien
    0.07
    asters
    0.07
     pend
    0.06
    MLE
    0.06
     Autor
    0.06
    оÑĢод
    0.06
     Campo
    0.06
    aka
    0.06
    rang
    0.06
    nds
    0.06
    Activations Density 0.002%

    No Known Activations