© 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. 54364
    Prev
    Next
    INDEX
    Explanations

    terms related to genetic elements and their functions

    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
     sonucunda
    -0.07
    ãĥ¼ãĥ³
    -0.07
     кÑĥÑĢи
    -0.07
    erli
    -0.06
    adesh
    -0.06
    odom
    -0.06
     Richards
    -0.06
    zap
    -0.06
    âĢIJâĢIJ
    -0.06
    ipse
    -0.06
    POSITIVE LOGITS
     chứa
    0.07
    enia
    0.07
     such
    0.07
    idebar
    0.07
    eyse
    0.07
     sẵn
    0.06
    reve
    0.06
    /column
    0.06
    oud
    0.06
     suche
    0.06
    Activations Density 0.039%

    No Known Activations