© 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. 83028
    Prev
    Next
    INDEX
    Explanations

    URLs and references to web content

    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
    uliar
    -0.06
    ayer
    -0.06
    usa
    -0.06
    ango
    -0.06
    du
    -0.06
    utherland
    -0.05
    ruit
    -0.05
    ation
    -0.05
    ultur
    -0.05
    480
    -0.05
    POSITIVE LOGITS
    odate
    0.07
    åij
    0.07
    serter
    0.07
    kuk
    0.06
    ÏĢε
    0.06
    incer
    0.06
    Powered
    0.06
    .Networking
    0.06
    _permalink
    0.06
    OPSIS
    0.06
    Activations Density 0.004%

    No Known Activations