© 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. 75998
    Prev
    Next
    INDEX
    Explanations

    references to structured sections and numerical organization in academic papers

    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
    905
    -0.07
    olla
    -0.06
    lassian
    -0.06
    ãģªãģĹ
    -0.06
    ÙĨØ©
    -0.06
    Aceptar
    -0.06
    OOT
    -0.06
    ulos
    -0.06
    üst
    -0.06
    ема
    -0.06
    POSITIVE LOGITS
    ugin
    0.07
    ãĤ¦ãĥ³
    0.07
    .scalablytyped
    0.07
     devoted
    0.07
    clud
    0.06
    ırak
    0.06
    /Dk
    0.06
    alian
    0.06
     Duis
    0.06
     omas
    0.06
    Activations Density 0.016%

    No Known Activations