© 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. 71283
    Prev
    Next
    INDEX
    Explanations

    references to institutions of higher education and political movements related to them

    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
    æľŃ
    -0.06
     sleeve
    -0.06
    aises
    -0.06
    antz
    -0.06
    à¹ģà¸Ĥ
    -0.06
    -inline
    -0.06
    vant
    -0.06
    ãĤ¯ãĤ»
    -0.06
    CLUDED
    -0.06
    lue
    -0.06
    POSITIVE LOGITS
     student
    0.09
     Students
    0.08
    åѦçĶŁ
    0.08
     students
    0.08
     campus
    0.08
     Student
    0.08
    camp
    0.07
    Students
    0.07
    student
    0.07
    Student
    0.07
    Activations Density 0.000%

    No Known Activations