© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 80745
    Prev
    Next
    INDEX
    Explanations

    questions and discussions related to self-reflection and existential inquiry

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
     Marino
    -0.07
    awk
    -0.07
    awks
    -0.07
     roli
    -0.06
    TAIL
    -0.06
    "profile
    -0.06
    ãģ¾ãĤĭ
    -0.06
    är
    -0.06
    ITED
    -0.06
    ê¼
    -0.06
    POSITIVE LOGITS
     recently
    0.12
     lately
    0.11
     my
    0.10
    recent
    0.08
     recent
    0.08
     today
    0.08
    让æĪij
    0.08
     Recently
    0.08
     mijn
    0.08
    Recently
    0.08
    Activations Density 0.144%

    No Known Activations