© 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 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. 126587
    Prev
    Next
    INDEX
    Explanations

    concepts related to survival and essential needs

    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
    ÑĤим
    -0.07
    失
    -0.07
    ť
    -0.06
    ngle
    -0.06
    çĥĪ
    -0.06
    alles
    -0.06
    dÃŃ
    -0.06
    á»ĵng
    -0.06
     Tat
    -0.06
    seau
    -0.06
    POSITIVE LOGITS
     functioning
    0.10
     survival
    0.08
     life
    0.08
     lives
    0.08
     survive
    0.08
    çĶŁæ´»
    0.08
     function
    0.07
     leben
    0.07
    function
    0.07
     жизни
    0.07
    Activations Density 0.025%

    No Known Activations