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

    Neuronpedia

    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. 57869
    Prev
    Next
    INDEX
    Explanations

    phrases related to experiential learning and student training opportunities

    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
    ductive
    -0.07
    emade
    -0.07
    oola
    -0.07
     Gim
    -0.07
    atu
    -0.07
    INF
    -0.06
    uish
    -0.06
    uur
    -0.06
    ocup
    -0.06
    uide
    -0.06
    POSITIVE LOGITS
     experience
    0.12
     exposure
    0.11
    experience
    0.10
     real
    0.09
     Experience
    0.09
     experiences
    0.08
     Exposure
    0.08
     learning
    0.08
     opportunities
    0.08
    (real
    0.08
    Activations Density 0.044%

    No Known Activations