© 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. 94464
    Prev
    Next
    INDEX
    Explanations

    phrases related to collections, organization, and systematic structures

    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
    tid
    -0.07
    RoutingModule
    -0.06
    uss
    -0.06
    dato
    -0.06
    ibu
    -0.06
    alone
    -0.06
    jer
    -0.06
    lez
    -0.06
    pent
    -0.06
    าม
    -0.06
    POSITIVE LOGITS
    .pa
    0.07
    mbH
    0.06
    OperationException
    0.06
    mekte
    0.06
    690
    0.06
    877
    0.06
    .ct
    0.06
    (CType
    0.06
    681
    0.05
    ｡
    0.05
    Activations Density 0.033%

    No Known Activations