© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 71291
    Prev
    Next
    INDEX
    Explanations

    phrases related to personal reflection and experiences

    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
    ilar
    -0.08
    uges
    -0.08
    olars
    -0.06
    arcer
    -0.06
    eddar
    -0.06
     deltas
    -0.06
    clave
    -0.06
     Bugün
    -0.06
    isphere
    -0.06
    .Core
    -0.06
    POSITIVE LOGITS
     oder
    0.09
    æĪĸèĢħ
    0.09
     maybe
    0.09
    ï¼ĮæĪĸ
    0.09
     perhaps
    0.09
     yoksa
    0.08
    vil
    0.08
     æĪĸ
    0.08
     atau
    0.08
     or
    0.07
    Activations Density 0.045%

    No Known Activations