© 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. 119351
    Prev
    Next
    INDEX
    Explanations

    references to "Bot" in various contexts, particularly related to flora and fauna

    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
    gency
    -0.07
    jvu
    -0.07
    aunch
    -0.07
    Ïīμα
    -0.07
    å¹ķ
    -0.06
    tte
    -0.06
    är
    -0.06
    ustin
    -0.06
    ocket
    -0.06
     optics
    -0.06
    POSITIVE LOGITS
    anical
    0.12
    swana
    0.11
    tega
    0.08
    ched
    0.08
    elho
    0.07
    ATAB
    0.07
    bersome
    0.07
    rel
    0.07
    leneck
    0.07
    enti
    0.07
    Activations Density 0.005%

    No Known Activations