© 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. 119274
    Prev
    Next
    INDEX
    Explanations

    qualifiers and expressions of opinion about concepts and experiences

    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
    ftar
    -0.07
    eder
    -0.06
    isinden
    -0.06
    ãģĶ
    -0.06
     or
    -0.06
    знаÑĩа
    -0.06
    (savedInstanceState
    -0.06
    oriously
    -0.06
    edin
    -0.06
    åĤĻ
    -0.06
    POSITIVE LOGITS
    ILD
    0.07
    ozÃŃ
    0.07
    é³
    0.07
     creo
    0.07
    æ¦
    0.07
    mmc
    0.07
    ±Ð¾ÑĤ
    0.07
     Exposure
    0.07
    rozen
    0.06
    ForResource
    0.06
    Activations Density 0.001%

    No Known Activations