© 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. 54327
    Prev
    Next
    INDEX
    Explanations

    terms related to machinery and specifically crushing equipment

    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
    -mini
    -0.06
    564
    -0.05
     constexpr
    -0.05
    ieval
    -0.05
     tug
    -0.05
     Laden
    -0.05
    ajan
    -0.05
    lasses
    -0.05
    inx
    -0.05
    .mybatisplus
    -0.05
    POSITIVE LOGITS
     dök
    0.07
     Yosh
    0.07
    ohl
    0.07
    бин
    0.06
    ãĤŃãĥ¥
    0.06
    ëĤ
    0.06
     leagues
    0.06
    ิà¸ĩห
    0.06
    ROC
    0.06
    ÚĺÙĩ
    0.06
    Activations Density 0.005%

    No Known Activations