© 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 EvalsExportsinterp-engineNEWAPI 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. 70289
    Prev
    Next
    INDEX
    Explanations

    instances of the word "address" in various forms

    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
    usal
    -0.07
    kyt
    -0.07
    á»ijt
    -0.07
    issen
    -0.07
    eyh
    -0.07
     takson
    -0.07
    Ùħارات
    -0.07
    Aceptar
    -0.07
    ucken
    -0.07
    xit
    -0.07
    POSITIVE LOGITS
     assembled
    0.09
    sembled
    0.08
     assembly
    0.07
     gathered
    0.07
     assemble
    0.06
     graduating
    0.06
     crowds
    0.06
    axon
    0.06
     Congress
    0.06
     assemblies
    0.06
    Activations Density 0.011%

    No Known Activations