© 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. 72796
    Prev
    Next
    INDEX
    Explanations

    terms related to farming and agriculture

    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
    Ù
    -0.07
    laus
    -0.07
    ÑģÑı
    -0.07
    gether
    -0.07
    erne
    -0.07
    /*č↵
    -0.07
    ochen
    -0.07
    zion
    -0.07
    aurus
    -0.07
    ernaut
    -0.07
    POSITIVE LOGITS
    stead
    0.14
    aceut
    0.10
    aceutical
    0.10
    acia
    0.08
    acias
    0.08
    sey
    0.07
    ington
    0.07
    aged
    0.07
    yard
    0.07
    ady
    0.07
    Activations Density 0.013%

    No Known Activations