© 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. 94792
    Prev
    Next
    INDEX
    Explanations

    businesses and services related to support and loss management

    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
    _Impl
    -0.06
    emoc
    -0.06
    amas
    -0.06
    άζ
    -0.06
    alth
    -0.05
     UsersController
    -0.05
     Locker
    -0.05
    618
    -0.05
     thereby
    -0.05
     whereas
    -0.05
    POSITIVE LOGITS
    arkin
    0.08
    urette
    0.07
    .nano
    0.07
    xBA
    0.07
    xBD
    0.07
    ään
    0.07
     ÙĦÙĪ
    0.07
    alim
    0.07
    figcaption
    0.07
    .fig
    0.07
    Activations Density 0.331%

    No Known Activations