© 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. 15-LLAMASCOPE-RES-131K
    11. 88493
    Prev
    Next
    INDEX
    Explanations

    references to historic places and designations

    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
    ç¿Ĵ
    -0.07
    AndView
    -0.06
    ahlen
    -0.06
    éļĽ
    -0.06
    tle
    -0.06
    ëłµ
    -0.06
    stdClass
    -0.06
     ÙħعÙĦÙĪÙħات
    -0.06
     Horton
    -0.06
    æݧ
    -0.06
    POSITIVE LOGITS
    oplevel
    0.07
    zk
    0.07
    ardy
    0.07
    zion
    0.06
    ượng
    0.06
    iaz
    0.06
    313
    0.06
    ooter
    0.06
    zos
    0.06
    ystems
    0.06
    Activations Density 0.002%

    No Known Activations