© 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 EvalsExportsinterp-engineNEWAPI 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. 17537
    Prev
    Next
    INDEX
    Explanations

    references to specific teams and scores 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
    γκο
    -0.07
    iationException
    -0.07
    laces
    -0.07
    ASIC
    -0.06
    ETIME
    -0.06
    ldb
    -0.06
    PFN
    -0.06
     Conc
    -0.06
    ofday
    -0.06
    -lfs
    -0.06
    POSITIVE LOGITS
    bies
    0.06
    ÃŃ
    0.06
    -Mart
    0.06
    ckett
    0.06
     Fest
    0.05
     stagnant
    0.05
    ฯ
    0.05
     ëĭµ
    0.05
    arat
    0.05
     Confidential
    0.05
    Activations Density 0.017%

    No Known Activations