Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 22-LLAMASCOPE-RES-131K
    6. 4891
    Prev
    Next
    INDEX
    Explanations

    references to time-duration or periods in a scientific context

    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
     Watt
    -0.06
     fict
    -0.06
     unsuccessful
    -0.06
     anecd
    -0.06
     apt
    -0.06
     acting
    -0.05
     observation
    -0.05
     Environmental
    -0.05
     proc
    -0.05
     environmental
    -0.05
    POSITIVE LOGITS
    ÐIJÑĢÑħÑĸв
    0.09
    naissance
    0.07
    inton
    0.07
    \e
    0.07
    udiant
    0.07
    -sama
    0.07
     reinterpret
    0.07
     Scholarship
    0.07
     scholarship
    0.06
    aklı
    0.06
    Activations Density 0.000%

    No Known Activations