© 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. 87037
    Prev
    Next
    INDEX
    Explanations

    numerical statistics, particularly those related to sports performance

    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
    PCP
    -0.07
    ovu
    -0.07
    /***/
    -0.07
    oze
    -0.07
    onya
    -0.06
    ovsky
    -0.06
     komp
    -0.06
    ần
    -0.06
    607
    -0.06
     Este
    -0.06
    POSITIVE LOGITS
    iero
    0.07
    apel
    0.06
    undi
    0.06
    poi
    0.06
     bon
    0.06
     cou
    0.06
     lifetime
    0.06
     اÙĦتÙĤ
    0.06
    ieri
    0.06
    mania
    0.06
    Activations Density 0.008%

    No Known Activations