© 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. 15-LLAMASCOPE-RES-131K
    11. 86755
    Prev
    Next
    INDEX
    Explanations

    key performance indicators and evaluations of effectiveness

    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
    UDGE
    -0.07
    ز
    -0.07
    aras
    -0.06
    udge
    -0.06
    GRP
    -0.06
    رÙĪس
    -0.06
    idget
    -0.06
     hab
    -0.06
    िषय
    -0.06
     motive
    -0.06
    POSITIVE LOGITS
    053
    0.07
    ailles
    0.07
    avir
    0.07
    roker
    0.07
    hardt
    0.07
    ảy
    0.07
    olem
    0.07
    ugg
    0.07
     excel
    0.06
    resa
    0.06
    Activations Density 0.010%

    No Known Activations