© 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. 15-LLAMASCOPE-RES-131K
    11. 88145
    Prev
    Next
    INDEX
    Explanations

    phrases related to water quality and management issues

    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
    ilty
    -0.06
     denominator
    -0.06
    =@
    -0.06
     twin
    -0.06
     Heb
    -0.05
    722
    -0.05
     crime
    -0.05
     extern
    -0.05
     unbe
    -0.05
     Ser
    -0.05
    POSITIVE LOGITS
    viol
    0.07
    -viol
    0.07
    lix
    0.07
    -trigger
    0.07
    inois
    0.07
    åijĪ
    0.07
     ActionType
    0.07
    oki
    0.07
    /action
    0.07
     levels
    0.07
    Activations Density 0.031%

    No Known Activations