© 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. 41615
    Prev
    Next
    INDEX
    Explanations

    elements related to digital or web-based data structures

    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
     swingers
    -0.07
    ught
    -0.07
    bero
    -0.07
    erot
    -0.07
    анÑĮ
    -0.06
     Blasio
    -0.06
    æĥħ
    -0.06
    é¦
    -0.06
    pend
    -0.06
    aran
    -0.06
    POSITIVE LOGITS
    acular
    0.07
    insky
    0.07
    jsonp
    0.06
    ago
    0.06
     country
    0.06
     Boone
    0.06
    akis
    0.06
    buckets
    0.06
    İ
    0.06
    onga
    0.06
    Activations Density 0.002%

    No Known Activations