© 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. 127427
    Prev
    Next
    INDEX
    Explanations

    statistics 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
    immel
    -0.07
    hausen
    -0.07
    zcze
    -0.07
    ibold
    -0.07
    formance
    -0.07
    osh
    -0.06
    UTTON
    -0.06
    ãģŀ
    -0.06
     Ãĸl
    -0.06
    avery
    -0.06
    POSITIVE LOGITS
    ìĶ©
    0.07
    ìĤ°
    0.07
     each
    0.06
     every
    0.06
    ä¸Ģ缴
    0.06
    ream
    0.06
     except
    0.06
    otor
    0.06
     twice
    0.06
    apor
    0.06
    Activations Density 0.009%

    No Known Activations