© 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. 30304
    Prev
    Next
    INDEX
    Explanations

    programming keywords related to namespaces and using directives

    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
    heim
    -0.06
    ascal
    -0.06
    ekt
    -0.06
    ucing
    -0.06
     acc
    -0.06
    tober
    -0.06
    λα
    -0.06
    bot
    -0.06
    ató
    -0.06
    cil
    -0.06
    POSITIVE LOGITS
    afone
    0.07
    SSION
    0.07
    ÏĥÏħ
    0.07
    ozy
    0.07
    éĸĵãģ«
    0.07
    ode
    0.06
    addtogroup
    0.06
    maz
    0.06
    æº
    0.06
    venta
    0.06
    Activations Density 0.002%

    No Known Activations