© 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. 9-LLAMASCOPE-RES-131K
    11. 96452
    Prev
    Next
    INDEX
    Explanations

    references to music and its contextual elements

    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
    odos
    -0.07
    Edition
    -0.06
    581
    -0.06
    osemite
    -0.06
    .ManyToMany
    -0.06
    umont
    -0.06
    hangi
    -0.06
     Äijôi
    -0.06
    698
    -0.06
    ragen
    -0.06
    POSITIVE LOGITS
    INESS
    0.07
     Analyst
    0.06
    eled
    0.06
    lei
    0.06
     RectTransform
    0.06
     PropertyChangedEventArgs
    0.06
    textfield
    0.06
    Separ
    0.06
     epidemic
    0.06
    CLAIM
    0.06
    Activations Density 0.001%

    No Known Activations