© 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. 94539
    Prev
    Next
    INDEX
    Explanations

    connections between students and support systems or mentorship 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
    adian
    -0.07
    udeau
    -0.07
    aviors
    -0.07
    lian
    -0.07
    orz
    -0.06
    agnet
    -0.06
     Presenter
    -0.06
    lect
    -0.06
     Stateless
    -0.06
    olumbia
    -0.06
    POSITIVE LOGITS
     pairs
    0.09
     pair
    0.08
     matched
    0.07
    Pairs
    0.07
     assigned
    0.07
     Pair
    0.07
     assignment
    0.07
     longitud
    0.06
    634
    0.06
    assigned
    0.06
    Activations Density 0.022%

    No Known Activations