© 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. 87371
    Prev
    Next
    INDEX
    Explanations

    terms related to USB devices and connectivity

    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
    avir
    -0.08
    евеÑĢ
    -0.07
    жÑĥ
    -0.07
    ystack
    -0.07
    enco
    -0.07
    ercial
    -0.07
    æłı
    -0.07
    acin
    -0.06
    iaz
    -0.06
    Scoped
    -0.06
    POSITIVE LOGITS
     circa
    0.06
    á»ĵi
    0.06
     join
    0.06
     connect
    0.06
     incompatible
    0.05
    joining
    0.05
    utan
    0.05
    862
    0.05
     Tong
    0.05
     wishlist
    0.05
    Activations Density 0.038%

    No Known Activations