© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 38987
    Prev
    Next
    INDEX
    Explanations

    coding-related terminology, especially concerning texture management and mathematical constructs involving identity matrices

    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
    osu
    -0.06
    ctor
    -0.06
    jar
    -0.06
    aura
    -0.06
     stron
    -0.06
    ãĥ¬ãĥ¼
    -0.06
     Jar
    -0.05
    .Reporting
    -0.05
    (optional
    -0.05
    _________________↵↵
    -0.05
    POSITIVE LOGITS
    /null
    0.12
    /no
    0.10
    /not
    0.08
    elerik
    0.08
    innitus
    0.08
    /plain
    0.07
    .INSTANCE
    0.07
    stown
    0.07
    åĿª
    0.07
    SENT
    0.07
    Activations Density 0.156%

    No Known Activations