© 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. 29671
    Prev
    Next
    INDEX
    Explanations

    references to system knowledge and understanding of established norms

    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
     Bou
    -0.07
    ifax
    -0.07
    #ab
    -0.07
     Nar
    -0.07
    ICODE
    -0.06
    ourn
    -0.06
    WO
    -0.06
    oad
    -0.06
    elden
    -0.06
    agger
    -0.06
    POSITIVE LOGITS
     familiar
    0.09
     we
    0.09
     known
    0.08
     as
    0.07
     recognizable
    0.07
     ÙĥÙħا
    0.07
     today
    0.07
     пÑĢивÑĭ
    0.07
     Fam
    0.07
    ortal
    0.07
    Activations Density 0.023%

    No Known Activations