© 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. 9-LLAMASCOPE-RES-131K
    11. 96305
    Prev
    Next
    INDEX
    Explanations

    SQL query components related to column selection and aggregation

    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
    icari
    -0.08
     Ãĸr
    -0.07
    ipher
    -0.07
    linkplain
    -0.07
    quette
    -0.07
    ائب
    -0.07
    amburger
    -0.07
    SENS
    -0.07
    æĪ¸
    -0.07
    á»Ń
    -0.07
    POSITIVE LOGITS
    378
    0.06
    olic
    0.06
    olie
    0.06
     respectively
    0.06
    sty
    0.05
    iar
    0.05
    iant
    0.05
    Stuff
    0.05
     Hawkins
    0.05
    672
    0.05
    Activations Density 0.007%

    No Known Activations