© 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. 118289
    Prev
    Next
    INDEX
    Explanations

    information related to sports transfers and related activities

    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
    okers
    -0.07
    deniz
    -0.07
     <*>
    -0.07
    ogens
    -0.07
    bourg
    -0.06
     लà¤ķ
    -0.06
    uchos
    -0.06
    owski
    -0.06
    odel
    -0.06
    cej
    -0.06
    POSITIVE LOGITS
     transfers
    0.07
     Transfer
    0.07
    .Transfer
    0.07
     lists
    0.07
     transactions
    0.07
     rum
    0.06
    Transfer
    0.06
     transfer
    0.06
    /free
    0.06
    /lists
    0.06
    Activations Density 0.015%

    No Known Activations