© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 97097
    Prev
    Next
    INDEX
    Explanations

    terms associated with vector graphics and their characteristics

    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
    isan
    -0.07
    olas
    -0.07
    leur
    -0.07
    å¯Ĵ
    -0.07
    olit
    -0.06
    amat
    -0.06
    LOOP
    -0.06
    primer
    -0.06
    ле
    -0.06
    ovo
    -0.06
    POSITIVE LOGITS
    gn
    0.07
     Poe
    0.06
     gn
    0.06
    alien
    0.06
    ipmap
    0.06
    лиÑĪ
    0.06
     Dre
    0.06
    puties
    0.06
    911
    0.06
    _tip
    0.06
    Activations Density 0.002%

    No Known Activations