© 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. 15-LLAMASCOPE-RES-131K
    11. 26876
    Prev
    Next
    INDEX
    Explanations

    phrases related to maintenance and repair needs

    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
    alink
    -0.07
    efe
    -0.07
    afa
    -0.07
    gnu
    -0.07
    جÙĪÛĮ
    -0.07
     ^↵
    -0.07
    peq
    -0.07
    ног
    -0.07
    anche
    -0.06
    iona
    -0.06
    POSITIVE LOGITS
     chances
    0.08
     ÑĤогда
    0.07
    ÑĢа
    0.06
     then
    0.06
    likelihood
    0.06
    Then
    0.06
    usch
    0.06
     entonces
    0.06
    onen
    0.06
    avage
    0.06
    Activations Density 0.013%

    No Known Activations