© 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. 28811
    Prev
    Next
    INDEX
    Explanations

    phrases related to aspirations and unfulfilled potential

    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
    oice
    -0.07
    .enumer
    -0.06
     Roo
    -0.06
     ÚĨØ´Ùħ
    -0.06
     Dob
    -0.06
    agh
    -0.06
     Dub
    -0.06
    ADO
    -0.06
    InParameter
    -0.06
     Ø·
    -0.06
    POSITIVE LOGITS
    uibModal
    0.07
    uem
    0.07
    Ø´ÙĨ
    0.06
    ctype
    0.06
    atica
    0.06
     unavailable
    0.06
    -Smith
    0.06
    /library
    0.06
     itself
    0.06
    oola
    0.06
    Activations Density 0.014%

    No Known Activations