© 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. 77802
    Prev
    Next
    INDEX
    Explanations

    references to sports competitions and championships

    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
     fault
    -0.07
    ascript
    -0.07
     odense
    -0.06
    ropp
    -0.06
    leur
    -0.06
     melts
    -0.06
    ãĥ¯ãĥ¼
    -0.06
     Lauderdale
    -0.06
    rowsable
    -0.06
    taÅŁ
    -0.06
    POSITIVE LOGITS
    opic
    0.07
    idal
    0.06
     verze
    0.06
    encies
    0.06
    åĢī
    0.06
    ÑģÑĤа
    0.06
    BERS
    0.06
    alcon
    0.06
    commit
    0.06
    bers
    0.06
    Activations Density 0.008%

    No Known Activations