© 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. 26627
    Prev
    Next
    INDEX
    Explanations

    references to local landmarks and heritage sites

    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
    jez
    -0.07
    )prepare
    -0.07
    assa
    -0.06
    iesz
    -0.06
    brook
    -0.05
    HeaderCode
    -0.05
    agle
    -0.05
    Ľi
    -0.05
     oceans
    -0.05
    UrlParser
    -0.05
    POSITIVE LOGITS
    åѦä¼ļ
    0.07
     ActionTypes
    0.07
    æĮĻ
    0.07
     operator
    0.07
    aby
    0.07
     Strauss
    0.07
     management
    0.07
    ographer
    0.07
     actionTypes
    0.07
    =@"
    0.07
    Activations Density 0.021%

    No Known Activations