© 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. 70161
    Prev
    Next
    INDEX
    Explanations

    references to critical analysis and evaluation

    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
    preload
    -0.07
    ilde
    -0.07
    "&
    -0.06
     ãĥ¼
    -0.06
    :async
    -0.06
    lesen
    -0.06
    oya
    -0.06
    DSA
    -0.06
    MetaData
    -0.06
    åįĩ
    -0.06
    POSITIVE LOGITS
     programme
    0.07
    imals
    0.06
    /alert
    0.06
    /DD
    0.06
    andom
    0.06
    wan
    0.06
    ANDOM
    0.06
     agendas
    0.06
    uras
    0.05
     thems
    0.05
    Activations Density 0.001%

    No Known Activations