© 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 EvalsExportsAPI 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. 96937
    Prev
    Next
    INDEX
    Explanations

    definitions and properties related to mathematical attractors and closures

    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
    v
    -0.06
     elev
    -0.06
    Dual
    -0.06
    ias
    -0.05
    isters
    -0.05
     Rip
    -0.05
    van
    -0.05
    à¥Ģप
    -0.05
    ZX
    -0.05
     risk
    -0.05
    POSITIVE LOGITS
    panse
    0.08
    .gdx
    0.07
     Ñģад
    0.07
    poons
    0.07
    umlu
    0.07
    adge
    0.07
    obia
    0.07
    ispecies
    0.07
    ValueCollection
    0.07
    chte
    0.07
    Activations Density 0.034%

    No Known Activations