© 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. 77406
    Prev
    Next
    INDEX
    Explanations

    specific terms and actions related to activities or modifications involving tools and equipment

    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
    enity
    -0.07
    patterns
    -0.07
    ẩm
    -0.06
    pattern
    -0.06
    éĢ£
    -0.06
    Concurrency
    -0.06
    anke
    -0.06
    bos
    -0.06
    cats
    -0.06
    883
    -0.06
    POSITIVE LOGITS
     ÑĥÑĩаÑģÑĤи
    0.07
    té
    0.07
    FIXME
    0.07
     abbiamo
    0.06
    ikk
    0.06
    aremos
    0.06
     (~
    0.06
     Nationals
    0.06
    íĮħ
    0.06
    éĢ¸
    0.06
    Activations Density 0.001%

    No Known Activations