© 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. 17-LLAMASCOPE-RES-131K
    11. 105860
    Prev
    Next
    INDEX
    Explanations

    concepts and definitions related to mathematical properties and solutions

    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
    alam
    -0.07
    .chapter
    -0.07
    رÙĪ
    -0.06
    ASS
    -0.06
    alo
    -0.06
    inks
    -0.06
    áºŃt
    -0.06
    peg
    -0.06
    ass
    -0.06
    orte
    -0.06
    POSITIVE LOGITS
    culate
    0.07
    ighb
    0.07
    енÑĤи
    0.07
     indicator
    0.07
     Indicator
    0.07
    inned
    0.07
    éĸ
    0.07
    ediÄŁi
    0.07
    sworth
    0.06
    stå
    0.06
    Activations Density 0.096%

    No Known Activations