© 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. 73933
    Prev
    Next
    INDEX
    Explanations

    references to artistic styles and their historical significance

    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
    associ
    -0.07
    ash
    -0.07
    achen
    -0.06
    heid
    -0.06
     å¹
    -0.06
    verting
    -0.06
    iphery
    -0.06
    reatest
    -0.06
    grese
    -0.06
    Associ
    -0.06
    POSITIVE LOGITS
    ernal
    0.07
    ìŀIJìĿ¸
    0.07
    uder
    0.07
     called
    0.06
     apt
    0.06
    usc
    0.06
    θα
    0.06
     rip
    0.06
    ánh
    0.06
    аÑĢÑĸв
    0.06
    Activations Density 0.065%

    No Known Activations