© 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. 15-LLAMASCOPE-RES-131K
    11. 89911
    Prev
    Next
    INDEX
    Explanations

    quotes from individuals in sports contexts

    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
    аÑģÑĤи
    -0.08
    clerosis
    -0.07
    ambi
    -0.07
    MSN
    -0.07
    alis
    -0.07
    arus
    -0.07
    boot
    -0.07
    ies
    -0.07
    ien
    -0.07
    acente
    -0.07
    POSITIVE LOGITS
     cann
    0.07
     comm
    0.06
    âĺħâĺħ
    0.06
     Anth
    0.06
     pinch
    0.06
     mole
    0.06
     sets
    0.05
     spiked
    0.05
    ITS
    0.05
    ippo
    0.05
    Activations Density 0.010%

    No Known Activations