© 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. 89049
    Prev
    Next
    INDEX
    Explanations

    phrases and words associated with installation and maintenance services

    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
    iah
    -0.07
    ered
    -0.07
    оÑĢо
    -0.07
    )))),
    -0.07
    ستاÙĨ
    -0.06
    æĺł
    -0.06
    /scripts
    -0.06
     moci
    -0.06
    ombat
    -0.06
    ¨¨
    -0.06
    POSITIVE LOGITS
    utter
    0.09
    emm
    0.08
    Operation
    0.08
     operation
    0.07
    ammen
    0.07
     Operation
    0.07
    ajar
    0.07
     Runtime
    0.07
    åij½
    0.07
    asion
    0.07
    Activations Density 0.018%

    No Known Activations