© 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. 40324
    Prev
    Next
    INDEX
    Explanations

    specific phrases about personal experiences and routines

    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
     your
    -0.13
    your
    -0.10
     Your
    -0.10
    Your
    -0.09
    ä½łçļĦ
    -0.09
     yourself
    -0.09
     YOUR
    -0.09
     ваÑĪ
    -0.09
     votre
    -0.07
    æĤ¨çļĦ
    -0.07
    POSITIVE LOGITS
     myself
    0.13
     tôi
    0.11
    ç»ĻæĪij
    0.11
    让æĪij
    0.10
     meiner
    0.10
    æĺ¯æĪij
    0.10
     saya
    0.10
    æĪijçļĦ
    0.09
    ï¼ĮæĪij
    0.09
     моÑĹ
    0.09
    Activations Density 0.068%

    No Known Activations