© 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. 5-LLAMASCOPE-RES-131K
    11. 125515
    Prev
    Next
    INDEX
    Explanations

    mathematical properties and operations involving set intersections and dimensions

    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
    ognito
    -0.07
    å±Ĭ
    -0.06
    ãĤ·ãĥ¼
    -0.06
     setFrame
    -0.06
    iov
    -0.06
    elles
    -0.06
    ÑĢоÑĩ
    -0.06
    EXPORT
    -0.06
    bei
    -0.06
    airo
    -0.06
    POSITIVE LOGITS
     Canton
    0.06
    ech
    0.06
    ria
    0.06
     Weber
    0.06
    ellipsis
    0.06
    raquo
    0.06
    507
    0.06
     rendered
    0.06
    _ros
    0.06
     tops
    0.06
    Activations Density 0.010%

    No Known Activations