© 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 EvalsExportsinterp-engineNEWAPI 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. 124229
    Prev
    Next
    INDEX
    Explanations

    numeric data and punctuation

    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
    .Dot
    -0.06
    Pont
    -0.06
     Gazette
    -0.06
    anine
    -0.06
    á»ĭch
    -0.06
    üz
    -0.06
    Æ¡
    -0.06
     اÙĦبÙĦد
    -0.06
    ÑĶв
    -0.06
    OGLE
    -0.06
    POSITIVE LOGITS
     London
    0.08
     New
    0.07
     Los
    0.07
    lug
    0.07
    ocus
    0.07
    Scalars
    0.07
     Beijing
    0.06
    é¤Ĭ
    0.06
    London
    0.06
    jis
    0.06
    Activations Density 0.006%

    No Known Activations