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

    Neuronpedia

    Jacobian LensNEW
    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. 58547
    Prev
    Next
    INDEX
    Explanations

    dates and events related to player transfers in sports context

    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
    iddi
    -0.07
    ira
    -0.07
    erson
    -0.06
    ekim
    -0.06
    CHAT
    -0.06
    ãĥªãĥ³ãĤ°
    -0.06
    Balancer
    -0.06
    ardy
    -0.06
    eling
    -0.06
    ARD
    -0.06
    POSITIVE LOGITS
     announced
    0.07
    etooth
    0.07
     announces
    0.06
    ez
    0.06
    ann
    0.06
    orget
    0.06
    ÑĢог
    0.06
    annabin
    0.06
    ozy
    0.06
     ANN
    0.06
    Activations Density 0.009%

    No Known Activations