© 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. 86254
    Prev
    Next
    INDEX
    Explanations

    references to sports and sporting events

    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
    poly
    -0.06
    urement
    -0.06
    eker
    -0.06
    suz
    -0.06
    UIT
    -0.06
    ham
    -0.06
     upside
    -0.06
    दर
    -0.06
    584
    -0.06
     baÅŁ
    -0.06
    POSITIVE LOGITS
    ovnÃŃ
    0.09
    ovnÄĽ
    0.08
    ive
    0.07
    sw
    0.07
    y
    0.07
    ÑĤивного
    0.07
    ãĥ¼ãĥĦ
    0.07
    sg
    0.07
    sm
    0.07
    ãĥ©ãĥ³ãĥī
    0.07
    Activations Density 0.014%

    No Known Activations