© 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. 76699
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the development and occurrence of relationships over 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
    urette
    -0.07
    ÅĻez
    -0.07
    лаÑģÑĤи
    -0.06
    iland
    -0.06
    WER
    -0.06
    994
    -0.06
    à¹Ģหà¸Ļ
    -0.06
    üst
    -0.06
     Airways
    -0.06
     Craig
    -0.06
    POSITIVE LOGITS
     overnight
    0.11
     Overnight
    0.11
     single
    0.09
    /single
    0.08
    single
    0.08
     SINGLE
    0.07
    isol
    0.07
     isolated
    0.07
     sudden
    0.07
    overn
    0.07
    Activations Density 0.021%

    No Known Activations