© 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. 60533
    Prev
    Next
    INDEX
    Explanations

    concepts related to maintenance and prolonging freshness or quality

    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
    MLS
    -0.07
    insky
    -0.06
     iff
    -0.06
    ajÄħ
    -0.06
    lot
    -0.06
     ==(
    -0.06
    .isBlank
    -0.06
     ausge
    -0.05
    ázd
    -0.05
    aland
    -0.05
    POSITIVE LOGITS
     until
    0.14
     longer
    0.14
    Until
    0.12
     till
    0.12
    until
    0.12
     Until
    0.12
    _until
    0.10
     hasta
    0.10
     longest
    0.10
     Longer
    0.09
    Activations Density 0.026%

    No Known Activations