© 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. 28265
    Prev
    Next
    INDEX
    Explanations

    terms related to product specifications and enhancements in technology

    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
    rouch
    -0.06
    elon
    -0.06
    _traits
    -0.06
    quin
    -0.06
    alin
    -0.06
    olor
    -0.06
    ãĥ«ãĥī
    -0.06
    omu
    -0.06
     Abdel
    -0.06
    zÃŃ
    -0.05
    POSITIVE LOGITS
    //{{
    0.08
    .sap
    0.08
     GmbH
    0.07
     Bayern
    0.07
    sap
    0.07
    +++
    0.07
     pi
    0.07
    aterno
    0.07
    Germany
    0.07
     Deutschland
    0.07
    Activations Density 0.003%

    No Known Activations