© 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. 15164
    Prev
    Next
    INDEX
    Explanations

    relationships involving data analysis, optimization, and the impacts of digital technologies

    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
    rak
    -0.07
    ÛĮتÛĮ
    -0.06
    ÙĦÛĮسÛĮ
    -0.06
     collo
    -0.06
     inflamm
    -0.06
    080
    -0.06
    170
    -0.06
     doubly
    -0.06
    -looking
    -0.06
    ?action
    -0.06
    POSITIVE LOGITS
    aña
    0.08
     københavn
    0.07
    omb
    0.07
    udden
    0.07
    ryfall
    0.07
    ylland
    0.07
     ÑĤоÑīо
    0.07
    elsea
    0.07
    <UnityEngine
    0.07
    Whilst
    0.07
    Activations Density 0.148%

    No Known Activations