© 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. 108154
    Prev
    Next
    INDEX
    Explanations

    references to visual and audio experiences with an emphasis on quality

    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
    ogui
    -0.07
    218
    -0.06
    619
    -0.06
    UnderTest
    -0.06
    morgan
    -0.06
    trak
    -0.06
    ÙĪاÙĨ
    -0.06
    608
    -0.06
    izzo
    -0.06
    950
    -0.06
    POSITIVE LOGITS
     Bootstrap
    0.07
    oran
    0.06
     Fax
    0.06
    accur
    0.06
    rich
    0.06
    nob
    0.06
    Bootstrap
    0.06
    _objs
    0.06
     rich
    0.06
    ãĥ³ãĥ
    0.06
    Activations Density 0.005%

    No Known Activations