© 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. 30500
    Prev
    Next
    INDEX
    Explanations

    references to shipping and delivery options

    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
    antro
    -0.08
    OrCreate
    -0.07
    enza
    -0.07
    schemas
    -0.07
    ToProps
    -0.06
    ElementException
    -0.06
    erties
    -0.06
    TypeDef
    -0.06
    visor
    -0.06
    (es
    -0.06
    POSITIVE LOGITS
    dda
    0.07
     orders
    0.07
    afb
    0.06
    eworld
    0.06
    cale
    0.06
     Stick
    0.06
    -orders
    0.06
     tun
    0.06
    æĦı
    0.06
    Stick
    0.06
    Activations Density 0.003%

    No Known Activations