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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 95496
    Prev
    Next
    INDEX
    Explanations

    mathematical terms and concepts, especially those related to restrictions and induced structures

    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
    kal
    -0.07
    á»Ń
    -0.07
    ubat
    -0.07
    stalk
    -0.06
    arde
    -0.06
    abra
    -0.06
     Nack
    -0.06
    á»ijc
    -0.06
    tul
    -0.06
    ãĤ¯ãĥĪ
    -0.06
    POSITIVE LOGITS
    804
    0.06
    806
    0.06
    IPP
    0.06
    812
    0.06
    pson
    0.06
    altung
    0.06
     Guid
    0.06
     onto
    0.06
    xED
    0.06
    817
    0.05
    Activations Density 0.024%

    No Known Activations