© 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. 9-LLAMASCOPE-RES-131K
    11. 96343
    Prev
    Next
    INDEX
    Explanations

    terms associated with college athletics and compensation

    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
    illon
    -0.07
    astos
    -0.07
    Äįit
    -0.07
    lean
    -0.07
    /todo
    -0.07
    uish
    -0.06
     поÑĢÑıдкÑĥ
    -0.06
    ixin
    -0.06
    finger
    -0.06
    ERGE
    -0.06
    POSITIVE LOGITS
    indo
    0.06
     Freed
    0.06
     scale
    0.06
     Guerr
    0.05
     free
    0.05
     zip
    0.05
    oken
    0.05
     prov
    0.05
    ssa
    0.05
     ASN
    0.05
    Activations Density 0.004%

    No Known Activations