© 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. 15-LLAMASCOPE-RES-131K
    11. 523
    Prev
    Next
    INDEX
    Explanations

    references to music-related shows and programming

    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
    oller
    -0.07
    Ľ°
    -0.07
     professional
    -0.06
    702
    -0.06
    inka
    -0.05
    ije
    -0.05
    jez
    -0.05
    lashes
    -0.05
    ivid
    -0.05
     discount
    -0.05
    POSITIVE LOGITS
    eki
    0.09
     constexpr
    0.07
    OfClass
    0.07
    ä¸ĢåĮº
    0.07
     reordered
    0.07
    ogi
    0.07
    getReference
    0.07
    ê´
    0.07
    kus
    0.07
     programu
    0.07
    Activations Density 0.010%

    No Known Activations