© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 126363
    Prev
    Next
    INDEX
    Explanations

    concepts and discussions related to the nature of time

    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
    iero
    -0.06
     spot
    -0.06
    даÑı
    -0.06
    enger
    -0.06
    jos
    -0.06
    ician
    -0.06
    Į¨
    -0.06
     Mez
    -0.06
     candidate
    -0.06
     success
    -0.06
    POSITIVE LOGITS
    /temp
    0.08
    .scalablytyped
    0.07
     ÑĩаÑģом
    0.07
    /time
    0.07
    ãģ®ãģĭ
    0.07
    tam
    0.07
    boru
    0.07
     Lords
    0.07
    (Time
    0.07
    avicon
    0.06
    Activations Density 0.017%

    No Known Activations