© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 71936
    Prev
    Next
    INDEX
    Explanations

    numerical values and statistics related to size or quantity

    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
     adultos
    -0.07
    HH
    -0.06
    ampler
    -0.06
     hardest
    -0.06
    asher
    -0.06
    é¡į
    -0.06
    ashing
    -0.06
    vars
    -0.05
    antha
    -0.05
    thed
    -0.05
    POSITIVE LOGITS
     smaller
    0.24
     lesser
    0.17
     lower
    0.16
     simpler
    0.14
    å°ı
    0.13
     shorter
    0.13
    lower
    0.13
     å°ı
    0.12
     small
    0.12
     lighter
    0.12
    Activations Density 0.093%

    No Known Activations