© 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. 87581
    Prev
    Next
    INDEX
    Explanations

    references to programming libraries and tools used in software development

    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
    ĵĺ
    -0.06
     Schl
    -0.06
     pointed
    -0.06
    elu
    -0.06
     impeachment
    -0.06
    ยว
    -0.06
    gis
    -0.06
    ativ
    -0.05
     Financial
    -0.05
    iesel
    -0.05
    POSITIVE LOGITS
    bens
    0.08
    azzi
    0.07
     Ferrari
    0.07
    utherford
    0.07
    .sul
    0.07
    eria
    0.07
    FRAME
    0.07
     setFrame
    0.07
    gnore
    0.07
    acher
    0.07
    Activations Density 0.023%

    No Known Activations