© 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. 56570
    Prev
    Next
    INDEX
    Explanations

    concepts related to artistic passion and the trade-offs involved in pursuing it

    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
    oom
    -0.07
    oda
    -0.07
    IQ
    -0.07
    ãĤīãģĦ
    -0.07
     heter
    -0.06
    endor
    -0.06
     cal
    -0.06
    iences
    -0.06
    ingen
    -0.06
     رسÙħ
    -0.06
    POSITIVE LOGITS
     passion
    0.10
     pure
    0.10
     hobby
    0.10
    pure
    0.09
     subs
    0.08
     gratis
    0.08
     gratuite
    0.08
     passionate
    0.08
    纯
    0.07
    gratis
    0.07
    Activations Density 0.040%

    No Known Activations