© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 62997
    Prev
    Next
    INDEX
    Explanations

    phrases discussing the consequences and impacts of various events and situations

    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
    urtle
    -0.08
    pyx
    -0.08
    isque
    -0.08
    'gc
    -0.08
    .getElements
    -0.07
    KeyValue
    -0.07
     ê·Ģ
    -0.07
    hled
    -0.07
    oque
    -0.07
    lein
    -0.07
    POSITIVE LOGITS
     effects
    0.08
    -effects
    0.07
    ona
    0.07
     of
    0.07
     Effects
    0.06
    781
    0.06
    853
    0.06
    itzer
    0.06
     Mes
    0.06
    effects
    0.06
    Activations Density 0.011%

    No Known Activations