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

    Neuronpedia

    Jacobian LensNEW
    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. 88419
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, primarily periods

    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
    #__
    -0.07
    á»ĵm
    -0.07
    ederland
    -0.07
    endas
    -0.07
    pageTitle
    -0.06
    ãģ¡ãĤĥ
    -0.06
     Sesso
    -0.06
    ηγ
    -0.06
    abela
    -0.06
    .super
    -0.06
    POSITIVE LOGITS
    MA
    0.06
    MLE
    0.06
    ond
    0.06
     MAV
    0.06
    ills
    0.06
     Motion
    0.06
    IA
    0.06
     Irving
    0.06
    odb
    0.06
     equivalent
    0.06
    Activations Density 0.001%

    No Known Activations