© 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. 4378
    Prev
    Next
    INDEX
    Explanations

    references to tennis performance statistics and achievements

    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
    Ïģκ
    -0.07
    kees
    -0.07
    landers
    -0.06
     poh
    -0.06
     dro
    -0.06
    orton
    -0.06
    jÃŃm
    -0.06
    dro
    -0.06
    poser
    -0.06
     Mitar
    -0.06
    POSITIVE LOGITS
    ENTE
    0.07
    ilha
    0.06
     éĦ
    0.06
    μη
    0.06
    770
    0.06
    اÙĤع
    0.06
     CascadeType
    0.06
    _Local
    0.06
    ente
    0.06
    open
    0.06
    Activations Density 0.003%

    No Known Activations