© 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. 83926
    Prev
    Next
    INDEX
    Explanations

    terms related to academic or scholarly resources

    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
    andre
    -0.07
    andr
    -0.06
    antar
    -0.06
     паÑĢа
    -0.06
    buch
    -0.06
    assy
    -0.06
    éijij
    -0.06
    олÑĮз
    -0.06
    llx
    -0.06
    ract
    -0.06
    POSITIVE LOGITS
     journals
    0.07
    ift
    0.07
    field
    0.07
     Preview
    0.07
    Ïĩή
    0.06
     unlike
    0.06
    Preview
    0.06
    articles
    0.06
    prech
    0.06
    üss
    0.06
    Activations Density 0.004%

    No Known Activations