© 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. 81141
    Prev
    Next
    INDEX
    Explanations

    phrases related to international relations and immigration

    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
     clos
    -0.07
     Wich
    -0.06
     manip
    -0.06
     Wenger
    -0.06
     hat
    -0.06
    ume
    -0.06
    ï¿
    -0.06
    {{{
    -0.06
     Simone
    -0.06
     оÑĤд
    -0.06
    POSITIVE LOGITS
    -collapse
    0.07
    -scrollbar
    0.07
    -overlay
    0.07
    isha
    0.07
    sha
    0.07
    achts
    0.06
    åĢĴ
    0.06
    -scroll
    0.06
    perty
    0.06
    uting
    0.06
    Activations Density 0.026%

    No Known Activations