© 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. 123957
    Prev
    Next
    INDEX
    Explanations

    HTML or XML code structure

    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
    eda
    -0.07
    loor
    -0.06
    essian
    -0.06
    еле
    -0.06
    attering
    -0.06
    modifiable
    -0.06
    loom
    -0.06
    ,âĢ¦↵↵
    -0.05
    getic
    -0.05
    agra
    -0.05
    POSITIVE LOGITS
    ivec
    0.08
    emachine
    0.07
    .shtml
    0.07
    inci
    0.06
    /tab
    0.06
    碼
    0.06
    ofire
    0.06
    .activ
    0.06
    .cent
    0.06
     code
    0.06
    Activations Density 0.026%

    No Known Activations