© 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. 15-LLAMASCOPE-RES-131K
    11. 90310
    Prev
    Next
    INDEX
    Explanations

    terms related to welding and inspection technologies

    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
     rozum
    -0.07
    elu
    -0.07
    /input
    -0.06
     åĨĨ
    -0.06
     buffering
    -0.06
    irsch
    -0.06
    pag
    -0.06
    VEL
    -0.06
    ROKE
    -0.06
    criptors
    -0.06
    POSITIVE LOGITS
    arf
    0.07
     Bran
    0.06
     skip
    0.06
     shop
    0.06
    odos
    0.06
     дÑĢÑĥго
    0.06
    ewis
    0.06
     handheld
    0.06
     fatigue
    0.06
     coupons
    0.06
    Activations Density 0.004%

    No Known Activations