© 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. 17-LLAMASCOPE-RES-131K
    11. 59901
    Prev
    Next
    INDEX
    Explanations

    titles and references related to geographical and geological mapping

    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
    gain
    -0.06
    imers
    -0.06
    rex
    -0.06
    ceae
    -0.06
    ipop
    -0.06
    ÃŃÅĻ
    -0.06
    ire
    -0.06
    stakes
    -0.06
    å¡ŀ
    -0.06
    ATAB
    -0.06
    POSITIVE LOGITS
    ĮĴ
    0.07
    (åľŁ
    0.07
    =T
    0.07
     Triumph
    0.07
     Tales
    0.07
     graz
    0.07
    -NLS
    0.07
     tr
    0.07
     amacıyla
    0.06
    viso
    0.06
    Activations Density 1.177%

    No Known Activations