© 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. 9-LLAMASCOPE-RES-131K
    11. 97387
    Prev
    Next
    INDEX
    Explanations

    sections and components of scientific papers or studies

    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
     Nur
    -0.06
    .shutdown
    -0.06
    avi
    -0.06
     vent
    -0.06
     Beg
    -0.05
     inn
    -0.05
     educated
    -0.05
    elan
    -0.05
     allen
    -0.05
    iac
    -0.05
    POSITIVE LOGITS
    Å¡t
    0.07
    enza
    0.07
    nable
    0.07
    anos
    0.07
    mdb
    0.07
    strt
    0.07
    addir
    0.07
    untime
    0.06
     Kurum
    0.06
    umhur
    0.06
    Activations Density 0.008%

    No Known Activations