© 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. 72660
    Prev
    Next
    INDEX
    Explanations

    references to ongoing projects or programming tasks

    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
    uele
    -0.07
    kil
    -0.07
    ects
    -0.06
    854
    -0.06
    &S
    -0.06
    /Page
    -0.06
    voÅĻ
    -0.06
    ills
    -0.06
    une
    -0.06
    regar
    -0.06
    POSITIVE LOGITS
     project
    0.07
    project
    0.07
    ozem
    0.07
    ona
    0.06
    >NN
    0.06
    argo
    0.06
    é¡¹çĽ®
    0.06
     projekt
    0.06
     VERY
    0.06
    _project
    0.06
    Activations Density 0.008%

    No Known Activations