© 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. 15-LLAMASCOPE-RES-131K
    11. 104135
    Prev
    Next
    INDEX
    Explanations

    instances of fluctuating room conditions or statuses

    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
    reon
    -0.07
     eing
    -0.07
    гÑĥ
    -0.07
     serviceName
    -0.07
    ãģ¼
    -0.07
    793
    -0.07
    bench
    -0.07
    ãĥ¼ãĥ«
    -0.07
    IMIT
    -0.07
    AGED
    -0.07
    POSITIVE LOGITS
     opened
    0.08
     closed
    0.07
     open
    0.07
    orida
    0.07
     reopened
    0.06
    inski
    0.06
     filled
    0.06
     full
    0.06
     ours
    0.06
    lland
    0.06
    Activations Density 0.040%

    No Known Activations