© 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. 107739
    Prev
    Next
    INDEX
    Explanations

    descriptors of software applications and frameworks

    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
    ottie
    -0.06
     Kingdom
    -0.06
    tec
    -0.06
     sen
    -0.06
     [
    -0.06
    441
    -0.06
     tall
    -0.06
     ende
    -0.05
     Sal
    -0.05
    tel
    -0.05
    POSITIVE LOGITS
     tool
    0.09
    å·¥åħ·
    0.08
    .tool
    0.08
    ÐIJÑĢÑħÑĸв
    0.08
     universal
    0.08
    tool
    0.08
     kå
    0.07
    naissance
    0.07
    .cent
    0.07
    _QMARK
    0.07
    Activations Density 0.027%

    No Known Activations