© 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. 89085
    Prev
    Next
    INDEX
    Explanations

    mentions of specific sports teams and their performances

    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
    ycl
    -0.09
    adb
    -0.07
    çĨ
    -0.07
    #
    -0.07
    batim
    -0.07
    cÃŃm
    -0.06
    uche
    -0.06
    affen
    -0.06
    lime
    -0.06
    rium
    -0.06
    POSITIVE LOGITS
     (~(
    0.07
     lad
    0.06
    cker
    0.06
    ÏĦÏħ
    0.06
     Progress
    0.06
    able
    0.06
     paid
    0.06
    ardy
    0.06
    imals
    0.06
    inka
    0.05
    Activations Density 0.033%

    No Known Activations