© 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. 41174
    Prev
    Next
    INDEX
    Explanations

    references to positions and movements in a sports context

    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
     kob
    -0.07
    .scalablytyped
    -0.07
     tav
    -0.06
    гов
    -0.06
    ografia
    -0.06
    corp
    -0.06
     eins
    -0.06
    еÑģп
    -0.06
    /umd
    -0.06
    lej
    -0.06
    POSITIVE LOGITS
    ocha
    0.06
    ANDING
    0.06
    ENTA
    0.06
    Inflater
    0.06
    617
    0.06
    ãģĦãģ§
    0.06
    Ń
    0.06
    elin
    0.05
    ayd
    0.05
    aton
    0.05
    Activations Density 0.008%

    No Known Activations