© 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. 30098
    Prev
    Next
    INDEX
    Explanations

    references to academic articles or publications

    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
     Dmit
    -0.07
    aby
    -0.07
    wo
    -0.07
    梨
    -0.07
    elmet
    -0.06
    abis
    -0.06
    éĥİ
    -0.06
    åºŃ
    -0.06
    hardt
    -0.06
    agos
    -0.06
    POSITIVE LOGITS
    anlar
    0.07
    ίκ
    0.06
    prech
    0.06
    ìļķ
    0.06
     aras
    0.06
    villa
    0.06
     Valencia
    0.06
    ,},↵
    0.06
    _procs
    0.06
    auen
    0.06
    Activations Density 0.003%

    No Known Activations