© 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. 87748
    Prev
    Next
    INDEX
    Explanations

    inquiries about artificial intelligence and neural networks

    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
    ISCO
    -0.07
    decorators
    -0.07
    antt
    -0.07
    gaard
    -0.07
    ç´
    -0.07
     multis
    -0.07
    _fds
    -0.07
    edio
    -0.07
    ovich
    -0.07
     bure
    -0.07
    POSITIVE LOGITS
     AI
    0.14
    AI
    0.12
     Artificial
    0.12
     ai
    0.10
    .ai
    0.10
    ai
    0.10
     Machine
    0.10
     machine
    0.10
     artificial
    0.10
    .AI
    0.09
    Activations Density 0.044%

    No Known Activations