© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 17093
    Prev
    Next
    INDEX
    Explanations

    references to future possibilities and aspirations

    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
     гаÑĢан
    -0.07
    preced
    -0.06
    ãĥ¼ãĥį
    -0.06
    ncia
    -0.06
    ìĦŃ
    -0.06
    _REUSE
    -0.06
    upos
    -0.06
    ãģ°ãģĭãĤĬ
    -0.06
    tec
    -0.06
    TestFixture
    -0.06
    POSITIVE LOGITS
     future
    0.21
     eventual
    0.19
     eventually
    0.19
    future
    0.18
     Eventually
    0.16
    Eventually
    0.16
     someday
    0.16
     later
    0.15
    .future
    0.15
    Future
    0.14
    Activations Density 0.058%

    No Known Activations