© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 29785
    Prev
    Next
    INDEX
    Explanations

    keywords related to animal behavior and interactions, particularly involving hunting and capturing

    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
    cess
    -0.07
    omu
    -0.07
    linger
    -0.06
    alloc
    -0.06
    ItemList
    -0.06
    ogue
    -0.06
    .cloudflare
    -0.06
    ovo
    -0.06
     Morm
    -0.06
    галÑĸ
    -0.06
    POSITIVE LOGITS
     GOODMAN
    0.07
     cach
    0.07
     trou
    0.06
     Ñģам
    0.06
    веÑģÑĤи
    0.06
     ><?
    0.06
    ÐļТ
    0.06
    setProperty
    0.06
    ük
    0.06
     iht
    0.06
    Activations Density 0.034%

    No Known Activations