© 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. 95059
    Prev
    Next
    INDEX
    Explanations

    significant numerical data and statistics

    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
    .sul
    -0.07
    .tap
    -0.07
    yh
    -0.07
    orrh
    -0.07
    alah
    -0.06
    nodoc
    -0.06
    MG
    -0.06
     OVERRIDE
    -0.06
    osto
    -0.06
     Stick
    -0.06
    POSITIVE LOGITS
    arel
    0.06
     footing
    0.05
     dem
    0.05
     Dem
    0.05
     lem
    0.05
    0.05
    æĹı
    0.05
    pie
    0.05
     Arb
    0.05
    Ø¢Ùħد
    0.05
    Activations Density 0.001%

    No Known Activations