© 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. 15-LLAMASCOPE-RES-131K
    11. 86438
    Prev
    Next
    INDEX
    Explanations

    terms and references related to programming structures and environments

    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
    ayne
    -0.07
    ÃŃch
    -0.06
     <*>
    -0.06
    atti
    -0.06
    bject
    -0.06
     smart
    -0.06
     jam
    -0.06
    ibur
    -0.06
     gam
    -0.06
    POSITIVE LOGITS
    quam
    0.07
    -producing
    0.07
    hora
    0.07
    "crypto
    0.06
    .Transactional
    0.06
     Nasıl
    0.06
    andaÅŁ
    0.06
    ource
    0.06
    USES
    0.06
    CreatedBy
    0.06
    Activations Density 0.026%

    No Known Activations