© 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. 15-LLAMASCOPE-RES-131K
    11. 87836
    Prev
    Next
    INDEX
    Explanations

    references to specific sporting events and their outcomes

    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
     Scho
    -0.06
    w
    -0.06
     overs
    -0.06
    оди
    -0.06
    ODO
    -0.06
     midnight
    -0.06
    åį
    -0.05
     activity
    -0.05
    arta
    -0.05
    î
    -0.05
    POSITIVE LOGITS
    ÙĨدÙĩ
    0.07
     cellForRowAtIndexPath
    0.07
     yesterday
    0.07
    hiba
    0.07
    infeld
    0.07
    ãĥ¼ãĥĵãĤ¹
    0.07
    มาร
    0.07
    dorf
    0.07
    esterday
    0.07
    onds
    0.06
    Activations Density 0.014%

    No Known Activations