© 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. 78637
    Prev
    Next
    INDEX
    Explanations

    elements related to educational opportunities and student engagement

    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
     Toy
    -0.07
    Toy
    -0.07
    anou
    -0.07
     karak
    -0.07
    allis
    -0.07
    одо
    -0.06
    _deinit
    -0.06
    pty
    -0.06
    CLUD
    -0.06
    gent
    -0.06
    POSITIVE LOGITS
     students
    0.20
     student
    0.18
     Students
    0.16
    students
    0.15
    åѦçĶŁ
    0.15
    student
    0.15
    Students
    0.14
     Student
    0.13
     íķĻìĥĿ
    0.12
    .student
    0.12
    Activations Density 0.277%

    No Known Activations