© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 2980
    Prev
    Next
    INDEX
    Explanations

    references to swords

    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
    udes
    -0.07
    ogy
    -0.07
    xt
    -0.07
    ÑĢиз
    -0.07
    xing
    -0.07
    exampleInput
    -0.07
    imers
    -0.07
    ude
    -0.07
    è¦
    -0.07
    disp
    -0.07
    POSITIVE LOGITS
    blade
    0.10
    fish
    0.09
     blade
    0.09
    -edge
    0.09
     blades
    0.08
    mith
    0.07
    (slice
    0.07
     slicing
    0.07
     sharpen
    0.07
     Blade
    0.07
    Activations Density 0.010%

    No Known Activations