© 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. 17-LLAMASCOPE-RES-131K
    11. 93753
    Prev
    Next
    INDEX
    Explanations

    terms associated with work and collaboration

    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
    istrov
    -0.08
    buch
    -0.07
    ollar
    -0.07
     Jac
    -0.06
    icas
    -0.06
    ulkan
    -0.06
    lagen
    -0.06
    ugs
    -0.06
    inkel
    -0.06
    ophil
    -0.06
    POSITIVE LOGITS
    IFO
    0.06
     adventure
    0.06
     partner
    0.06
     closely
    0.06
    ÑĢÑĸд
    0.06
    ourd
    0.06
     minh
    0.06
     mom
    0.06
    .mutable
    0.05
    ÑĢÑıдÑĥ
    0.05
    Activations Density 0.013%

    No Known Activations