© 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. 126364
    Prev
    Next
    INDEX
    Explanations

    references to industrial consumption and usage statistics

    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
    reesome
    -0.06
    uali
    -0.06
    avana
    -0.06
    loor
    -0.06
    ades
    -0.06
     Kız
    -0.06
    ãĤĵãģª
    -0.06
    ansi
    -0.06
    unes
    -0.05
    uÃŃ
    -0.05
    POSITIVE LOGITS
     consumption
    0.17
     Consumption
    0.15
     consumed
    0.13
     consume
    0.13
    consum
    0.12
    _consum
    0.11
     Consum
    0.11
    Consum
    0.11
    consume
    0.11
     usage
    0.11
    Activations Density 0.093%

    No Known Activations